© 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. 33508
    Prev
    Next
    INDEX
    Explanations

    what do you think

    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
    èªĵ
    -0.09
    esses
    -0.09
     GK
    -0.08
    èı¡
    -0.08
    å½»åºķ
    -0.08
    ä¸įè¦ģåĨį
    -0.08
    å½¢æĪIJçļĦ
    -0.07
    çłģ
    -0.07
    ä¸įèĥ½åĨį
    -0.07
    襻
    -0.07
    POSITIVE LOGITS
    æĤ¨åIJĮæĦı
    0.11
    itore
    0.10
    engers
    0.10
    ç§ī
    0.10
    åīįè¿Ľ
    0.10
    ijkl
    0.09
    常
    0.09
    _DC
    0.09
    elin
    0.09
    ullo
    0.09
    Activations Density 0.013%

    No Known Activations