© 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. 49002
    Prev
    Next
    INDEX
    Explanations

    names of coaches

    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
    éĿ´
    -0.09
    EFAULT
    -0.08
    éŀĭ
    -0.08
    åħį责声æĺİ
    -0.08
    åħ¨æĿij
    -0.08
     Ler
    -0.08
    å¢ĥ
    -0.08
    åĤ¨èĥ½
    -0.08
    趾
    -0.08
    èĢ³
    -0.08
    POSITIVE LOGITS
     ohio
    0.10
     pars
    0.09
    ä¿¡æģ¯åıijå¸ĥ
    0.09
    åĨĽå·¥
    0.09
    åķ¡
    0.09
    osoph
    0.09
    好çľĭçļĦ
    0.09
     bunk
    0.09
    èĮ´
    0.08
    éĥ¨åĪĨåĨħ容
    0.08
    Activations Density 0.040%

    No Known Activations