© 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. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 57566
    Prev
    Next
    INDEX
    Explanations

    live up, live again, living in

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-32b-saes/saes_Qwen_Qwen3-32B_batch_top_k/resid_post_layer_32
    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
    uez
    -0.10
    èĩªåĪ¶
    -0.08
    èİ«åIJįåħ¶å¦Ļ
    -0.08
     Shared
    -0.08
    åĹ·
    -0.08
     ol
    -0.08
     shared
    -0.08
     оÑĤкÑĢÑĭва
    -0.08
     Dow
    -0.08
    çķ¸å½¢
    -0.08
    POSITIVE LOGITS
    bjerg
    0.11
    æĭĬ
    0.11
    人大
    0.10
    çĶ¨å¾®ä¿¡
    0.10
    éĵ¡
    0.10
    stüt
    0.09
    ç¿İ
    0.09
    ç©¿
    0.09
    çijļ
    0.09
    ieber
    0.09
    Activations Density 0.022%

    No Known Activations