© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-8B
    5. 18-RESID-BATCHTOPK-65K__L0-80
    7. 220
    Prev
    Next
    INDEX
    Explanations

    stories behind the influential picturesmethodology behind thatpurpose behind themtheory behind EFTstories behind the hit songslogic behind feed-forwardidea behind that annoying sloganpurpose behind an affairdrivers behind these fundamental changesmeaning behind it

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-8b-saes/saes_Qwen_Qwen3-8B_batch_top_k/resid_post_layer_18
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    åħ´èĩ´
    -0.25
     enough
    -0.23
     ****************************************************************************
    -0.21
    Enough
    -0.21
    /or
    -0.20
     again
    -0.20
    еÑĩение
    -0.20
    ville
    -0.20
    문íĻĶ
    -0.19
     against
    -0.19
    POSITIVE LOGITS
    诸å¦Ĥ
    0.27
    è¿Ļåľº
    0.26
    è¿Ļä¸ĢåĪĩ
    0.26
    ä»Ģä¹Īåij¢
    0.24
    æŃ¤æ¬¡
    0.23
    çIJ¥
    0.22
     choosing
    0.22
    “
    0.22
    åIJĦ项
    0.21
    éĤ£ä»½
    0.21
    Activations Density 0.038%

    No Known Activations