© 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. 30105
    Prev
    Next
    INDEX
    Explanations

    bowling and activities

    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
    ãĥ£
    -0.09
    æĹłå½¢
    -0.09
    éĻĢ
    -0.09
    iT
    -0.09
    ä½Ĺ
    -0.09
    äº¤æĽ¿
    -0.09
    arend
    -0.08
    oral
    -0.08
     nast
    -0.08
    驼
    -0.08
    POSITIVE LOGITS
    /or
    0.10
    à´´
    0.10
    Ñīи
    0.10
    brook
    0.09
    iers
    0.09
    大家åĪĨ享
    0.08
    æ®Ħ
    0.08
     fant
    0.08
    isma
    0.08
    led
    0.08
    Activations Density 0.004%

    No Known Activations