© 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. 6464
    Prev
    Next
    INDEX
    Explanations

    prepared to

    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
    éºĴ
    -0.09
    lic
    -0.09
     dáng
    -0.08
     кÑĢови
    -0.08
    éļĻ
    -0.08
    деÑģÑıÑĤ
    -0.08
    rypton
    -0.08
     доп
    -0.08
     dod
    -0.08
    æı£
    -0.08
    POSITIVE LOGITS
    ness
    0.13
    erval
    0.12
    éĿŀ常好çļĦ
    0.10
    ç»ĦåĽ¢
    0.09
    odos
    0.09
     RVA
    0.09
    å·´æĭī
    0.09
    _SRV
    0.09
    ä¸įæĿ¥
    0.09
    ä¸ĩæĪ·
    0.09
    Activations Density 0.015%

    No Known Activations