© 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. 5433
    Prev
    Next
    INDEX
    Explanations

    quotation attribution dash

    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
    ä¸ĢåĪĩéĥ½
    -0.10
    çļĦä¸Ģ项
    -0.09
    å²ij
    -0.09
     simil
    -0.09
    ени
    -0.09
    ä¸ĢåĪĩ
    -0.08
    é¢Ĥ
    -0.08
    èĻIJ
    -0.08
    plevel
    -0.08
    -loading
    -0.08
    POSITIVE LOGITS
    merce
    0.10
    vox
    0.10
    .jquery
    0.08
    æľīåħ³éĥ¨éŨ
    0.08
    occup
    0.08
    å½ĵäºĭ
    0.08
    _RT
    0.08
    _DM
    0.08
    eci
    0.08
    _relu
    0.08
    Activations Density 0.034%

    No Known Activations