© 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. 7524
    Prev
    Next
    INDEX
    Explanations

    turn of the century

    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
     bore
    -0.08
    urm
    -0.08
    esa
    -0.08
    kah
    -0.08
    ocre
    -0.08
    åŁŁ
    -0.08
    éĢł
    -0.08
     cose
    -0.08
    ç«ĭå¿Ĺ
    -0.08
     Shelf
    -0.07
    POSITIVE LOGITS
    家éŨåı£
    0.10
    amil
    0.09
    å«Ķ
    0.09
    èĻ½è¯´
    0.09
    身边çļĦ
    0.09
    AMIL
    0.09
    ç±³åħ°
    0.09
    åħ¨äº§ä¸ļéĵ¾
    0.09
    ç»¿åľ°
    0.09
    ç»ĻåŃ©åŃIJ
    0.09
    Activations Density 0.003%

    No Known Activations