© 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. 31775
    Prev
    Next
    INDEX
    Explanations

    has to do with

    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
    à¤ł
    -0.09
    åĹľ
    -0.09
    rys
    -0.09
    orm
    -0.09
    çݳ
    -0.09
    ensa
    -0.08
     коÑĤоÑĢого
    -0.08
    æĪ³
    -0.08
    .pref
    -0.08
    sville
    -0.08
    POSITIVE LOGITS
    -done
    0.09
    agas
    0.09
    elite
    0.09
     Fresno
    0.08
    çļĦ带é¢Ĩ
    0.08
    wend
    0.08
     geh
    0.08
     undone
    0.08
    å¤
    0.08
    æĺİç¡®è§Ħå®ļ
    0.08
    Activations Density 0.043%

    No Known Activations