© 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. 30255
    Prev
    Next
    INDEX
    Explanations

    names before copyright or license

    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
    æĿŃå·ŀå¸Ĥ
    -0.09
    涪
    -0.09
    ateurs
    -0.09
    ateur
    -0.09
    çĥŁçģ«
    -0.09
    æ»
    -0.09
    åĭĸ
    -0.09
    涿
    -0.09
    ä¸Ģåı£æ°Ķ
    -0.09
    à¸īà¸ļ
    -0.09
    POSITIVE LOGITS
    iture
    0.08
    ноÑģ
    0.08
    loor
    0.08
    _coll
    0.08
     neut
    0.08
    (IT
    0.07
     Pil
    0.07
    ики
    0.07
    åħ¸
    0.07
    管çIJĨ模å¼ı
    0.07
    Activations Density 0.093%

    No Known Activations