© 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. 16917
    Prev
    Next
    INDEX
    Explanations

    from time to time

    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
    驹
    -0.12
    åĴĮæĶ¯æĮģ
    -0.10
    å¢ħ
    -0.09
    åľ¨äº¬
    -0.09
    tools
    -0.08
    è¿Ľä¸ĢæŃ¥
    -0.08
    åĵªéĩĮ
    -0.08
    itch
    -0.08
    è¿ĺ以为
    -0.08
    cus
    -0.08
    POSITIVE LOGITS
    çīĪæĿĥå½Ĵ
    0.11
    нÑĮ
    0.10
    ivent
    0.09
    /of
    0.09
    ÑĩиÑģлен
    0.09
    ppers
    0.09
    æµģéĢļ
    0.08
    åľ°
    0.08
    æī°
    0.08
    odian
    0.08
    Activations Density 0.004%

    No Known Activations