© 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. 38593
    Prev
    Next
    INDEX
    Explanations

    figure out

    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
    _heap
    -0.10
    椹
    -0.09
    沤
    -0.09
    æĬij
    -0.09
    ç¥ļ
    -0.09
    ancell
    -0.09
    spar
    -0.09
     Heath
    -0.09
    CHIP
    -0.09
    gué
    -0.08
    POSITIVE LOGITS
    åĩºåı£
    0.09
    ä¸Ńç¾İ
    0.08
    åĮĹç¾İ
    0.08
    chy
    0.08
    çī¢
    0.08
    大çīĩ
    0.08
     Dro
    0.08
    解æķ£
    0.08
    ç¥
    0.08
    寸
    0.08
    Activations Density 1.265%

    No Known Activations