© 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. 58516
    Prev
    Next
    INDEX
    Explanations

    class of year

    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
    rote
    -0.09
    çªĿ
    -0.08
    .Std
    -0.08
    妥
    -0.08
     passage
    -0.08
    æŃ¤é¡¹
    -0.08
    éļıæĦı
    -0.08
    çķı
    -0.08
    Unc
    -0.08
    CLI
    -0.07
    POSITIVE LOGITS
    åĴĮåľ°åĮº
    0.12
    åIJįçīĩ
    0.10
    æĨ©
    0.10
    ortal
    0.10
    ç¼Ń
    0.09
    è¯
    0.09
    èĭ¦èĭ¦
    0.09
    دس
    0.09
    åıįä¹ĭ
    0.09
    bows
    0.09
    Activations Density 0.009%

    No Known Activations