© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 21641
    Prev
    Next
    INDEX
    Explanations

    crew or crews

    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
    ater
    -0.10
    avel
    -0.09
    建åĨĽ
    -0.09
    æķ£æŃ¥
    -0.09
    èĥĮæĻ¯ä¸ĭ
    -0.08
    æłijæŀĿ
    -0.08
    صب
    -0.08
    umo
    -0.08
    çĦ¶èĢĮ
    -0.08
    ãĥ³ãĤ°
    -0.08
    POSITIVE LOGITS
    mares
    0.09
    稷
    0.09
    ILER
    0.09
    ailles
    0.09
    edis
    0.08
    Merit
    0.08
    å¨ĺ
    0.08
    Compatible
    0.08
    edo
    0.08
     Everett
    0.08
    Activations Density 0.006%

    No Known Activations