© 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. 50958
    Prev
    Next
    INDEX
    Explanations

    project and experience

    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·ĭ
    -0.09
    fra
    -0.08
    ÌĢ
    -0.08
    requent
    -0.08
    æııç»ĺ
    -0.08
    èIJ¥éĢł
    -0.08
    .chapter
    -0.08
    allon
    -0.08
    bote
    -0.08
    è§ĴéĢIJ
    -0.08
    POSITIVE LOGITS
    é¦Ĩ
    0.10
    pped
    0.09
    ç¼ļ
    0.09
    peg
    0.09
    å±ħ家
    0.09
     Bugs
    0.09
    Jud
    0.09
    åĮºåŁŁåĨħ
    0.09
    pes
    0.08
    æ¦Ľ
    0.08
    Activations Density 0.168%

    No Known Activations