© 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. 33074
    Prev
    Next
    INDEX
    Explanations

    major event or development

    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
    æ¥ļ
    -0.10
    rie
    -0.08
    .times
    -0.08
    drv
    -0.08
    Rew
    -0.08
    ewhere
    -0.08
    htag
    -0.08
    åĨįåĬłä¸Ĭ
    -0.08
     thượng
    -0.08
    åĨł
    -0.08
    POSITIVE LOGITS
    æĥĬ人
    0.11
     Dresses
    0.09
    ProcessEvent
    0.09
    ptom
    0.09
    axed
    0.09
    Bins
    0.09
    osit
    0.09
    æĽ²æĬĺ
    0.08
    è¡£çī©
    0.08
    ä¸ĢæĬĬ
    0.08
    Activations Density 0.314%

    No Known Activations