© 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. Qwen3-14B
    5. 20-RESID-BATCHTOPK-65K__L0-80
    7. 13027
    Prev
    Next
    INDEX
    Explanations

    suffix "-us" or "-ose"

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-14b-saes/saes_Qwen_Qwen3-14B_batch_top_k/resid_post_layer_20
    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
    æµĶ
    -0.22
    à¸Ńà¸ļ
    -0.20
    bler
    -0.19
    积
    -0.19
    seau
    -0.19
    ercise
    -0.18
    çķĻè¨Ģ
    -0.18
    ç±³å°Ķ
    -0.18
    hana
    -0.18
    æĦŁåħ´è¶£
    -0.18
    POSITIVE LOGITS
     dangling
    0.18
    åĬłå·¥
    0.18
     Ign
    0.17
    овиÑĩ
    0.17
     Se
    0.17
     Villa
    0.17
    mos
    0.17
    Ign
    0.16
    å¹´ãģ®
    0.16
     swe
    0.16
    Activations Density 0.007%

    No Known Activations