© 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. 54305
    Prev
    Next
    INDEX
    Explanations

    town hall

    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
    æľīæĿĥ
    -0.10
    SEN
    -0.10
    enze
    -0.10
    骼
    -0.09
    ngth
    -0.09
    年人
    -0.09
    ç¥ĸåĽ½
    -0.09
    ius
    -0.09
    ä¸İæѤ
    -0.09
    èī¯å¥½
    -0.09
    POSITIVE LOGITS
    _prof
    0.10
    æīĢåľ¨åľ°
    0.09
    mate
    0.09
    大楼
    0.09
    è¶ĭ
    0.08
    old
    0.08
    æĭĪ
    0.08
    راء
    0.08
    8
    0.07
    5
    0.07
    Activations Density 0.012%

    No Known Activations