© 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. 39667
    Prev
    Next
    INDEX
    Explanations

    arnia, Lewis, percutaneous, derived xenografts

    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
    纪å½ķ
    -0.10
     Mats
    -0.10
    mv
    -0.10
     statically
    -0.09
    _fps
    -0.09
    ä»İä¸ļ
    -0.08
    unde
    -0.08
    éĩįå¿ĥ
    -0.08
    岩
    -0.08
    agog
    -0.08
    POSITIVE LOGITS
    åĦ¿ç«¥
    0.11
    Interop
    0.09
    .Writer
    0.09
    åħĴç«¥
    0.09
    æIJģ
    0.09
    è¿ĻæĿ¡è·¯
    0.09
    ulin
    0.08
    éŃĶåħ½
    0.08
    åĵij
    0.08
    å¼Ĥåij³
    0.08
    Activations Density 0.078%

    No Known Activations