© 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. 49404
    Prev
    Next
    INDEX
    Explanations

    software updates

    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
    ç»
    -0.10
     Marino
    -0.10
    éĿĵ丽
    -0.09
    .wrapper
    -0.09
    åĪ¶éĢłä¸ļ
    -0.09
    产éĶĢ
    -0.09
    marvin
    -0.09
    èĢģå®ŀ
    -0.09
    frag
    -0.09
    å¥łå®ļäºĨ
    -0.09
    POSITIVE LOGITS
    æĽ´æĸ°
    0.14
     updates
    0.14
     update
    0.13
    updates
    0.12
    update
    0.12
     Updates
    0.11
     cáºŃp
    0.11
    .UPDATE
    0.11
    Update
    0.11
    åįĩ级
    0.11
    Activations Density 0.145%

    No Known Activations