© 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. 56215
    Prev
    Next
    INDEX
    Explanations

    pick up

    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
    积累äºĨ
    -0.09
    asons
    -0.09
    èĿĮ
    -0.09
    顶å±Ĥ
    -0.08
    æĬ½åıĸ
    -0.08
    建档
    -0.08
    _pull
    -0.08
     صÙģ
    -0.08
    OPS
    -0.08
    lek
    -0.08
    POSITIVE LOGITS
    èĭij
    0.09
     Impossible
    0.09
    åĩ¡
    0.09
     ÑĢеж
    0.08
    头
    0.08
     graded
    0.08
     Lud
    0.08
    对äºİæĪij们
    0.08
     heavier
    0.08
    _Rel
    0.08
    Activations Density 0.016%

    No Known Activations