© 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. 39518
    Prev
    Next
    INDEX
    Explanations

    in which

    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
    éĴ¿
    -0.09
    æľĿ
    -0.09
    tee
    -0.09
    кÑĥп
    -0.09
    anda
    -0.08
    roud
    -0.08
    åĭ¿
    -0.08
    已达
    -0.08
    ilda
    -0.08
     Pere
    -0.08
    POSITIVE LOGITS
    æĮĤéĴ©
    0.11
    åĸĩåıŃ
    0.09
    å¾ĹçĽĬ
    0.09
    åĪ°åºķæĺ¯
    0.09
    æ³ĵ
    0.09
    è¿ĻäºĽå¹´
    0.09
    /assert
    0.09
    velle
    0.09
    _hooks
    0.09
    _aspect
    0.09
    Activations Density 0.171%

    No Known Activations