© 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. 54568
    Prev
    Next
    INDEX
    Explanations

    critical events and concepts

    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
     Guth
    -0.10
    æ½ľåĬĽ
    -0.09
    æĪIJè¯Ń
    -0.09
    owered
    -0.08
    æijĩ
    -0.08
    ç¿ķ
    -0.08
    纯
    -0.08
    _TAGS
    -0.08
    ¯¯
    -0.08
    .promise
    -0.08
    POSITIVE LOGITS
     Critical
    0.12
     critical
    0.11
    critical
    0.10
    æĢ¥éľĢ
    0.10
    Critical
    0.10
    _CRITICAL
    0.10
    临
    0.09
    ç½ijåıĭè¯Ħ论
    0.09
     jun
    0.09
    ä¸ĩåĪĨ
    0.09
    Activations Density 0.064%

    No Known Activations