© 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. 39059
    Prev
    Next
    INDEX
    Explanations

    avoided, avoid, run from

    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
    æĢł
    -0.11
    å®ĺæĸ¹å¾®ä¿¡
    -0.10
    éĵºè®¾
    -0.10
    ewe
    -0.09
    æ°ĶåĢĻ
    -0.09
    縻
    -0.09
    究竣æĺ¯
    -0.08
    èĢ½
    -0.08
    åĪ°åºķæĺ¯
    -0.08
     premature
    -0.08
    POSITIVE LOGITS
    éģ¿å¼Ģ
    0.16
    åĽŀéģ¿
    0.14
    éģ¿
    0.13
    éģ¿åħį
    0.13
    å°½éĩı
    0.13
     avoided
    0.13
    éģ¿ãģij
    0.12
    avoid
    0.12
    è¿ľç¦»
    0.12
    ç»ķ
    0.12
    Activations Density 0.065%

    No Known Activations