© 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. 17494
    Prev
    Next
    INDEX
    Explanations

    match or matches

    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
    æĿ¥çľĭçľĭ
    -0.09
    thon
    -0.09
    licity
    -0.09
    æijĨ
    -0.08
    ä¸Ģéģĵ
    -0.08
    çĶŁçĶŁ
    -0.08
    arton
    -0.08
    UDIO
    -0.08
    å¼ĵ
    -0.08
    mlin
    -0.08
    POSITIVE LOGITS
    å¿ĥæĦı
    0.11
     Ñģобой
    0.11
    elle
    0.10
    éĶľ
    0.09
    客æĪ·éľĢæ±Ĥ
    0.09
    ucid
    0.09
    èĥĥåı£
    0.09
    æľ´ç´ł
    0.09
    æ´Ľåħĭ
    0.09
     reality
    0.08
    Activations Density 0.050%

    No Known Activations