© 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. 27546
    Prev
    Next
    INDEX
    Explanations

    diagnoses and disorders

    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
    idian
    -0.08
    ogne
    -0.08
    oug
    -0.08
    allback
    -0.08
    æijĦ
    -0.08
    SSIP
    -0.08
    emaker
    -0.08
     Blond
    -0.08
    å»ĵ
    -0.08
    (prom
    -0.08
    POSITIVE LOGITS
    èIJĿ
    0.13
    çĹĩ
    0.11
    cia
    0.10
     disorder
    0.09
    ç¥ĸåĽ½
    0.09
     Disorder
    0.09
    èĬ±éĴ±
    0.09
    /general
    0.08
    Ñĩи
    0.08
    æĶ¿åºľéĩĩè´Ń
    0.08
    Activations Density 0.050%

    No Known Activations