© 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. 18984
    Prev
    Next
    INDEX
    Explanations

    section, policy, or page

    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
    ç§ī
    -0.08
     Ñģобой
    -0.08
    èĩĨ
    -0.08
    jac
    -0.08
     Hem
    -0.07
    uthor
    -0.07
    ä¹İ
    -0.07
    ertext
    -0.07
    çļĦæĺ¯
    -0.07
    ä¸ĢäºĮ
    -0.07
    POSITIVE LOGITS
    æģIJæĢķ
    0.09
    éĥ½æĥ³
    0.09
    åı¯èĥ½åıijçĶŁ
    0.09
    ForMember
    0.09
    绽
    0.09
    ä½Ĩæĺ¯æĪij
    0.09
    éĢī项
    0.08
    åķµ
    0.08
    dek
    0.08
    åĶĽ
    0.08
    Activations Density 0.188%

    No Known Activations