© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 12152
    Prev
    Next
    INDEX
    Explanations

    types of

    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¿Ļç§įæĸ¹æ³ķ
    -0.11
    çĦī
    -0.11
    赡
    -0.09
    çĻ½éĽª
    -0.09
    IRS
    -0.09
    å²·
    -0.09
     Gone
    -0.08
    èĻij
    -0.08
    rections
    -0.08
    缦
    -0.08
    POSITIVE LOGITS
    æ¸ļ
    0.09
    çļĦåıijçĶŁ
    0.09
    åIJĦæł·
    0.09
     things
    0.09
    严峻
    0.09
    uala
    0.08
     sever
    0.08
    åıijçĶŁåľ¨
    0.08
    å¿ĥæĢĿ
    0.08
     ÑģовеÑĢ
    0.08
    Activations Density 0.024%

    No Known Activations