© 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. 54414
    Prev
    Next
    INDEX
    Explanations

    economic or rape crisis

    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
    ibri
    -0.08
    .stage
    -0.08
    ugal
    -0.08
    åIJĥ
    -0.08
     Burg
    -0.08
    ç´ł
    -0.08
    -of
    -0.08
    ä¸įçĶ¨
    -0.08
    Eu
    -0.08
    wort
    -0.08
    POSITIVE LOGITS
    åĵĤ
    0.10
    éĹ®ä¸ĸ
    0.09
    裱
    0.09
    Ñħо
    0.09
    geist
    0.09
    Heavy
    0.09
    ÑĢоÑĪ
    0.09
    ABLE
    0.08
    éĹªçĥģ
    0.08
    欢åij¼
    0.08
    Activations Density 0.004%

    No Known Activations