© 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. 23049
    Prev
    Next
    INDEX
    Explanations

    is a descriptive connector

    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
    åIJĦèĩªçļĦ
    -0.11
    æ¢ĵ
    -0.10
    å¿ĺè®°äºĨ
    -0.10
    ä»Ļå¢ĥ
    -0.09
    _NAMESPACE
    -0.09
    éĴŀ
    -0.09
    å¹Į
    -0.09
    IVEN
    -0.09
    ingle
    -0.09
    åĨĴçĿĢ
    -0.08
    POSITIVE LOGITS
    åĢij
    0.12
    们éĥ½
    0.10
    cie
    0.10
    们çļĦ
    0.10
    getConfig
    0.08
     Steph
    0.08
    wers
    0.08
    èĢĮåľ¨
    0.08
    kowski
    0.08
    lets
    0.08
    Activations Density 0.326%

    No Known Activations