© 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. 31854
    Prev
    Next
    INDEX
    Explanations

    fwlink /?

    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
    æĹĥ
    -0.10
    annel
    -0.09
    ignment
    -0.09
    .mvp
    -0.09
    æ¥Ķ
    -0.09
    utsch
    -0.09
    ager
    -0.09
     Gund
    -0.09
    åĿŀ
    -0.09
    oke
    -0.09
    POSITIVE LOGITS
    缸å½ĵ
    0.09
    cestor
    0.08
    ìĭľìĦ¤
    0.08
    æµ´
    0.08
    flix
    0.08
    erring
    0.08
    害
    0.07
    ç¬Ķè®°
    0.07
    åIJŀ
    0.07
    ycl
    0.07
    Activations Density 0.001%

    No Known Activations