© 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. 6384
    Prev
    Next
    INDEX
    Explanations

    consecutive

    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
    使å¾Ĺ
    -0.10
    rawid
    -0.09
    /lab
    -0.09
    asted
    -0.08
    avery
    -0.08
    íĥij
    -0.08
    _REUSE
    -0.08
    .bz
    -0.08
    ruk
    -0.08
    linky
    -0.08
    POSITIVE LOGITS
    æĪijèĩªå·±
    0.09
    åīįæīĢ
    0.09
    å±ŀäºİèĩªå·±
    0.08
    èĩªæĿ¥
    0.08
    è¾Ĩ车
    0.08
    åīĮ
    0.08
    è¹ij
    0.08
     consecutive
    0.08
    -ever
    0.08
    满äºĨ
    0.08
    Activations Density 0.734%

    No Known Activations