© 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. 39471
    Prev
    Next
    INDEX
    Explanations

    given by or to someone

    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
    ingly
    -0.11
    دÙĪÙĨ
    -0.10
    ë§IJ
    -0.10
    detect
    -0.09
    åŀ¢
    -0.09
     minded
    -0.09
    alli
    -0.09
    ä¸įåģľ
    -0.09
    åĽłåľ°
    -0.09
    leur
    -0.09
    POSITIVE LOGITS
    à¹īำ
    0.11
    棹
    0.10
    ance
    0.09
    çŀ©çĽ®
    0.09
    çľ¼åīį
    0.09
    chy
    0.09
    ìļ±
    0.09
    çĸ£
    0.09
    èµ°å»Ĭ
    0.09
    esses
    0.08
    Activations Density 0.039%

    No Known Activations