© 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. 10253
    Prev
    Next
    INDEX
    Explanations

    weeks and months

    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
    éĽĦåİļ
    -0.09
     confisc
    -0.09
     вÑĢемен
    -0.08
    ä¸įåIJĪ
    -0.08
    atura
    -0.08
    æ²£
    -0.08
    åŃļ
    -0.08
    Incoming
    -0.08
    æ£į
    -0.08
    hood
    -0.08
    POSITIVE LOGITS
    éĻ¤å¤ĸ
    0.11
     Ñģобой
    0.11
    ķìĿ¸
    0.09
    ลำ
    0.09
    ä½ľèĢħæľ¬äºº
    0.09
    ald
    0.08
    å«ģ
    0.08
    &&(
    0.08
    alfa
    0.08
    HeaderCode
    0.08
    Activations Density 0.004%

    No Known Activations