© 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. 48560
    Prev
    Next
    INDEX
    Explanations

    choking game, fits, reflex, aspiration

    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
    æªĢ
    -0.10
     toes
    -0.09
    èħ°
    -0.09
    mins
    -0.09
    ãģ²ãģ¨ãģ¤
    -0.09
    PTR
    -0.08
    榴
    -0.08
    ajs
    -0.08
    ANI
    -0.08
     tent
    -0.08
    POSITIVE LOGITS
    åijĽ
    0.14
    åĻİ
    0.12
    æĨĭ
    0.10
     choking
    0.09
    èĤ¿
    0.09
    åĸĿæ°´
    0.09
     internals
    0.09
    ulpt
    0.09
    课åłĤ
    0.09
    åĿIJä¸ĭ
    0.09
    Activations Density 0.034%

    No Known Activations