© 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. 62472
    Prev
    Next
    INDEX
    Explanations

    copyright attribution

    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
    BBBB
    -0.09
    aries
    -0.09
    幺
    -0.09
    线ä¸ĭ
    -0.08
    สว
    -0.08
    eddar
    -0.08
    combe
    -0.08
    .tagName
    -0.08
     Savings
    -0.08
    ols
    -0.08
    POSITIVE LOGITS
    è°¶
    0.11
    ç½²
    0.11
    åĢŃ
    0.09
    alion
    0.09
     frank
    0.09
    é¼»åŃIJ
    0.08
    åĩºå¤Ħ
    0.08
    èĪĽ
    0.08
    éĶĻäºĨ
    0.08
    è±Ĩ
    0.08
    Activations Density 0.015%

    No Known Activations