© 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. 23594
    Prev
    Next
    INDEX
    Explanations

    historical concepts or events

    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
    ble
    -0.09
    èĵ¬
    -0.09
    dale
    -0.08
    æīĢåľ¨
    -0.08
    oned
    -0.08
    èĥ½åIJ¦
    -0.08
    oom
    -0.08
    aries
    -0.08
     fore
    -0.08
    dre
    -0.08
    POSITIVE LOGITS
    ideo
    0.10
    ENCE
    0.10
    æĬķèµĦåŁºéĩij
    0.10
    LEM
    0.10
    ä¸ĭæĿ¥çļĦ
    0.10
    积水
    0.10
    æ°Ķ温
    0.09
    è§Ĥåħī
    0.09
    éªij
    0.09
    _ADAPTER
    0.09
    Activations Density 0.037%

    No Known Activations