© 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. 22397
    Prev
    Next
    INDEX
    Explanations

    copyright information

    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
    -Russian
    -0.14
    æ®ĸ
    -0.10
    缴éĢļ车
    -0.09
    侮辱
    -0.09
    佬
    -0.09
    ä¸ĢæĬĬ
    -0.09
    첨
    -0.09
    Reviewed
    -0.09
    SENT
    -0.09
    KeyId
    -0.09
    POSITIVE LOGITS
     rÃłng
    0.12
     havoc
    0.11
    art
    0.10
    (RE
    0.10
    ponse
    0.10
    ราว
    0.10
    leigh
    0.09
    efined
    0.09
    (R
    0.09
    amped
    0.09
    Activations Density 0.910%

    No Known Activations