© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 35900
    Prev
    Next
    INDEX
    Explanations

    team names

    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
    è¿ĻæĶ¯
    -0.10
    à¹Į
    -0.10
    äºİæĺ¯æĪij
    -0.09
     Ridley
    -0.09
    Aws
    -0.09
    ä¸ĢæĶ¯
    -0.09
     Gors
    -0.09
     çalÄ±ÅŁm
    -0.09
    isode
    -0.09
    顾
    -0.08
    POSITIVE LOGITS
    ÑĤай
    0.09
    äºĭåĦ¿
    0.09
    roid
    0.08
    haft
    0.08
    åĦ¿
    0.08
    åĸī
    0.08
    æĤłæĤł
    0.08
    åŃ°
    0.08
    èĻļ
    0.07
    osos
    0.07
    Activations Density 0.143%

    No Known Activations