© 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. 57549
    Prev
    Next
    INDEX
    Explanations

    member of Parliament

    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
    ลำ
    -0.10
    éŁ³åĵį
    -0.10
    iability
    -0.09
    好çľĭ
    -0.09
    åĬ©éķ¿
    -0.09
    åĵ¥ä¼¦æ¯Ķäºļ
    -0.09
    ç¾İæĦŁ
    -0.08
     ChÃŃ
    -0.08
    pawn
    -0.08
    éĢģè¾¾
    -0.08
    POSITIVE LOGITS
    åľ¨äº¬
    0.10
    人éĹ´
    0.10
    大èĩ£
    0.09
    PCS
    0.09
    adden
    0.09
    ä¸į对
    0.09
     Luk
    0.09
     Bere
    0.09
    pyx
    0.08
    第ä¸Ģéĥ¨
    0.08
    Activations Density 0.252%

    No Known Activations