© 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. 35120
    Prev
    Next
    INDEX
    Explanations

    detail and touches

    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
    æ»Ķ
    -0.09
    ä¸įåıĹ
    -0.09
    åİĨåı²æĸ°
    -0.09
     Reeves
    -0.09
    iert
    -0.09
    ä¸ī大
    -0.09
    å£
    -0.08
    .Bad
    -0.08
    __.__
    -0.08
    _INTERRUPT
    -0.08
    POSITIVE LOGITS
    ç»ĨèĬĤ
    0.26
     detail
    0.17
    ç»Ĩå¾®
    0.15
     Detail
    0.15
     details
    0.15
    ç»Ĩèĩ´
    0.14
    detail
    0.14
     Details
    0.13
    /detail
    0.13
    ç»Ĩå¿ĥ
    0.13
    Activations Density 0.039%

    No Known Activations