© 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. 18216
    Prev
    Next
    INDEX
    Explanations

    satisfy demands/requests/tastes

    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
    åĽŀäºĭ
    -0.09
    spot
    -0.09
    轻轻
    -0.09
    jes
    -0.09
    zon
    -0.08
    pad
    -0.08
    vature
    -0.08
    ãĥ¬ãĤ¹
    -0.08
    æıŃ示
    -0.08
    uccess
    -0.08
    POSITIVE LOGITS
    ä¸įäºĨ
    0.13
    好å¥ĩå¿ĥ
    0.11
    dio
    0.10
    å¸ĤåľºéľĢæ±Ĥ
    0.09
    çŁ¥æĥħ
    0.09
    asty
    0.09
    å¾ĹäºĨ
    0.09
    侧ç»ĵæŀĦæĢ§
    0.09
    ably
    0.09
    ment
    0.08
    Activations Density 0.014%

    No Known Activations