© 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. 50035
    Prev
    Next
    INDEX
    Explanations

    off and away

    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
    èµ·åºĬ
    -0.10
    æł¸å¿ĥåĮº
    -0.09
     Roy
    -0.08
    éĢļè¡Į
    -0.08
    alking
    -0.08
    èµ·æĿ¥
    -0.08
    æī¶
    -0.08
    ymmetric
    -0.08
    xing
    -0.08
    íĿ¬
    -0.08
    POSITIVE LOGITS
     Off
    0.10
    (off
    0.09
    Off
    0.09
    åģļ强
    0.09
    ev
    0.09
     off
    0.08
     Away
    0.08
    /off
    0.08
    åĽ¢éķ¿
    0.08
    rey
    0.08
    Activations Density 0.031%

    No Known Activations