© 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. 49250
    Prev
    Next
    INDEX
    Explanations

    php copyright

    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
    gMaps
    -0.13
    mPid
    -0.10
    matchCondition
    -0.10
    taboola
    -0.10
    æ±Ŀ
    -0.09
    _depend
    -0.09
    ermal
    -0.09
    ë®
    -0.08
    actionDate
    -0.08
    aths
    -0.08
    POSITIVE LOGITS
    ķìĿ¸
    0.08
    åĮķ
    0.08
    çŁŃçŁŃ
    0.08
    èIJľ
    0.08
    丧
    0.08
    æģ¤
    0.08
    æĥħ趣
    0.08
    ãĤĴéĢļãģĹãģ¦
    0.08
    2
    0.07
    7
    0.07
    Activations Density 0.063%

    No Known Activations