© 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. 47703
    Prev
    Next
    INDEX
    Explanations

    really + positive/negative descriptor

    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
    PS
    -0.08
    æĽ´åħ·
    -0.08
    å¤ļå±Ĥ次
    -0.08
    elier
    -0.08
    idable
    -0.08
    èµ°å¾Ĺ
    -0.07
    wnd
    -0.07
     Lat
    -0.07
    ribbon
    -0.07
    lap
    -0.07
    POSITIVE LOGITS
    ãģ³
    0.11
    åıijæĮ¥äºĨ
    0.10
    ddit
    0.10
    éķ¿èĢģ
    0.10
    éĴ¹
    0.10
    ãģªãģıãģª
    0.10
    é«ĺçļĦ
    0.10
    ä¿ĥè¿ĽäºĨ
    0.10
    éĴĿ
    0.09
    åĺ±
    0.09
    Activations Density 0.022%

    No Known Activations