© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 38402
    Prev
    Next
    INDEX
    Explanations

    restore or renew

    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
    onymous
    -0.09
    ogan
    -0.09
    è´¨åľ°
    -0.08
    èļĤèļģ
    -0.08
    .instagram
    -0.08
    ÑĪив
    -0.08
    æŶè£ħ
    -0.08
     Vân
    -0.08
    ald
    -0.08
    untime
    -0.08
    POSITIVE LOGITS
    ÑĩÑĮ
    0.09
    åĪİ
    0.09
    sources
    0.08
    ä¹ĭæĹħ
    0.08
    lags
    0.08
    HAV
    0.08
    å·¥ä½ľä½ľé£İ
    0.08
    uate
    0.08
    ally
    0.08
    åįķ身
    0.08
    Activations Density 0.006%

    No Known Activations