© 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. 57036
    Prev
    Next
    INDEX
    Explanations

    figure or season

    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
    sworth
    -0.10
    RIES
    -0.09
     tide
    -0.09
    æ±Ģ
    -0.09
    æī¿åĬŀ
    -0.09
    é¸Ń
    -0.08
    éĢł
    -0.08
    æĿ¡çº¦
    -0.08
    ä¸į失
    -0.08
    å¿ĥ缮ä¸Ń
    -0.08
    POSITIVE LOGITS
    宣
    0.10
    QueryString
    0.10
    INO
    0.10
     voks
    0.09
    ä¸īä½į
    0.09
    atrice
    0.09
    äºĨæĪijçļĦ
    0.09
    ä¸į足
    0.09
    _nonce
    0.09
    ather
    0.09
    Activations Density 0.009%

    No Known Activations