© 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. 27667
    Prev
    Next
    INDEX
    Explanations

    US history

    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
    ÙĦاØŃ
    -0.09
    ×ķת
    -0.09
    éĵ¿
    -0.09
    HUD
    -0.09
    .setTo
    -0.09
     cref
    -0.09
    OSH
    -0.09
    åĴĮåıijå±ķ
    -0.09
    åIJ¯è¿ª
    -0.09
    ToDate
    -0.08
    POSITIVE LOGITS
    unic
    0.09
    виз
    0.09
    UNCH
    0.08
     Bethlehem
    0.08
     attitude
    0.08
    aurus
    0.08
     Contributor
    0.08
    สว
    0.08
    ä¸ĢæŃ¥
    0.08
    å°¤åħ¶æĺ¯
    0.08
    Activations Density 0.053%

    No Known Activations