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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-8B
    5. 18-RESID-BATCHTOPK-65K__L0-80
    7. 2977
    Prev
    Next
    INDEX
    Explanations

    land value

    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
     cuck
    -0.26
    yon
    -0.25
    oustic
    -0.22
    éħ¸å¥¶
    -0.22
    วà¸Ļ
    -0.21
     guest
    -0.21
    æħĭ
    -0.21
     Library
    -0.21
    Library
    -0.21
    -online
    -0.21
    POSITIVE LOGITS
    使çĶ¨æĿĥ
    0.30
    éĢīåĿĢ
    0.30
    裸
    0.30
    åľ°åĿĹ
    0.28
     landscaping
    0.27
     layouts
    0.27
    éĵºè®¾
    0.27
    /location
    0.26
    éĶĢåĶ®æ¸łéģĵ
    0.25
    åľŁåľ°
    0.24
    Activations Density 0.019%

    No Known Activations