© 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. 11905
    Prev
    Next
    INDEX
    Explanations

    units of measurement

    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
    åĪĿæģĭ
    -0.11
    кÑĥÑĢ
    -0.10
    黯
    -0.10
    群
    -0.09
    éĢ»è¾ij
    -0.09
    欹
    -0.09
    .enter
    -0.09
    éĽªå±±
    -0.09
    ä½°
    -0.09
    åĨ²éĶĭ
    -0.08
    POSITIVE LOGITS
     UK
    0.09
    èĭ±
    0.09
    åIJ¬åIJ¬
    0.09
    english
    0.09
    _expr
    0.08
    outs
    0.08
     quart
    0.08
    æĸ¤
    0.08
    åĪĽéĢłåĩº
    0.08
    èĭ±å¯¸
    0.08
    Activations Density 0.085%

    No Known Activations