© 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. 17083
    Prev
    Next
    INDEX
    Explanations

    attributing information from sources

    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
    é¢Ĩ
    -0.10
    èĪ«
    -0.10
    å¥ļ
    -0.09
    åĹĶ
    -0.09
    çĪ±æĥħ
    -0.09
    çī¡
    -0.09
    åĸľæ¬¢åIJĥ
    -0.09
    壮è§Ĥ
    -0.09
    .Reference
    -0.09
    羡
    -0.09
    POSITIVE LOGITS
    æIJģ
    0.10
    åı¯éĿł
    0.09
    çĪĨæĸĻ
    0.09
    åij
    0.08
    çľĭåĪ°äºĨ
    0.08
    åijĬè¯ī她
    0.08
    agged
    0.08
    oding
    0.08
    å§ij
    0.08
    ä¸ĢåIJį
    0.07
    Activations Density 0.035%

    No Known Activations