© 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. 48647
    Prev
    Next
    INDEX
    Explanations

    back to

    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
    ugh
    -0.10
    çļĦåĽŀçŃĶ
    -0.10
    èĬ¡
    -0.09
    ERA
    -0.09
    ä¸ŃæľĢ
    -0.09
    izona
    -0.09
    åĪ°äºĨ
    -0.09
    ë¦ĩ
    -0.09
    ä¸įåĪ°
    -0.09
    å¾Ĥ
    -0.09
    POSITIVE LOGITS
    elon
    0.10
    纥
    0.09
    obby
    0.09
    wald
    0.09
     basics
    0.08
    ieve
    0.08
    landers
    0.08
    wards
    0.08
    Ñīин
    0.08
    åİŁæĿ¥çļĦ
    0.08
    Activations Density 0.026%

    No Known Activations