© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 9808
    Prev
    Next
    INDEX
    Explanations

    matrix associations

    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
    lez
    -0.09
    åīįæīĢ
    -0.09
    ote
    -0.09
    usive
    -0.08
    acious
    -0.08
    ÑĢÑĥж
    -0.08
    kek
    -0.08
    ../../../
    -0.08
    æ±
    -0.08
    _nsec
    -0.08
    POSITIVE LOGITS
    rm
    0.11
    å¢Ģ
    0.11
    ial
    0.10
    æ®Ĵ
    0.10
    ially
    0.10
    rics
    0.10
    å¼ĢæĿ¥
    0.10
    otr
    0.09
    å¾Īæĥ³
    0.09
    è°£è¨Ģ
    0.09
    Activations Density 0.048%

    No Known Activations