© 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. 33193
    Prev
    Next
    INDEX
    Explanations

    how to solve

    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
    ousel
    -0.09
    oints
    -0.09
    åĽŀäºĭ
    -0.09
    èijŃ
    -0.08
    ass
    -0.08
    aus
    -0.08
    lands
    -0.08
    ãģĤãĤĬãģ¾ãģĻãģĮ
    -0.08
     mile
    -0.08
    ulse
    -0.08
    POSITIVE LOGITS
    ä¹ĭéģĵ
    0.14
    ä¸įäºĨ
    0.14
    ì±ħ
    0.13
    åĬŀæ³ķ
    0.12
    itaire
    0.12
    iden
    0.12
    åı¯æĥ³
    0.12
    ftware
    0.11
    аÑĤоÑĢ
    0.11
     Nurs
    0.11
    Activations Density 0.112%

    No Known Activations