© 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. 6326
    Prev
    Next
    INDEX
    Explanations

    energy, electric, unit, bills

    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
    路边
    -0.10
    èĥ¡åŃIJ
    -0.09
     Doming
    -0.09
    лÑĥÑĪ
    -0.09
    鹧
    -0.09
    åıijå±ķ缮æłĩ
    -0.09
     airspace
    -0.09
    æĪ¢
    -0.09
    æĸŁ
    -0.08
    ä¿ĥ
    -0.08
    POSITIVE LOGITS
    å¥ī
    0.11
     bills
    0.09
    _bill
    0.09
    ergy
    0.09
    ä¸įå®Į
    0.09
    èµ°å¾Ĺ
    0.08
    èµ°
    0.08
    .methods
    0.08
     Bills
    0.08
    iap
    0.08
    Activations Density 0.039%

    No Known Activations