© 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. 35706
    Prev
    Next
    INDEX
    Explanations

    recruiting and offers

    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
    иÑĤел
    -0.10
    éļ¼
    -0.09
     Contest
    -0.09
    èĢĮæĺ¯
    -0.08
    subs
    -0.08
    à¸Ńล
    -0.08
    à¸ģรรม
    -0.08
    pbs
    -0.08
     ngo
    -0.08
    _MEDIUM
    -0.08
    POSITIVE LOGITS
    人éĢł
    0.11
    åĪ°ä½į
    0.10
    ameron
    0.10
    vice
    0.10
    å¿ĥå¢ĥ
    0.09
    åĿļ
    0.09
     spokes
    0.09
    osi
    0.09
    èĶĵ
    0.09
    åĬłçĽŁ
    0.09
    Activations Density 0.009%

    No Known Activations