© 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. 57433
    Prev
    Next
    INDEX
    Explanations

    fit you or your needs

    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
    .defer
    -0.08
    ç©¿è¶Ĭ
    -0.08
    vious
    -0.08
    toy
    -0.08
    /editor
    -0.08
    hind
    -0.08
    æĵİ
    -0.08
     dap
    -0.08
    å¥Ĺè£ħ
    -0.08
     Beg
    -0.08
    POSITIVE LOGITS
    å¾Ĺå¾Ī
    0.11
    ä¸ŃåĽ½ä¼łç»Ł
    0.11
    æĪij们çļĦ
    0.11
    å½ĵæŶçļĦ
    0.10
    å½ĵåīį
    0.10
    çķ¶æĻĤ
    0.10
    æĦŁ
    0.10
    è¿Ļåĩł
    0.10
    ouri
    0.10
    å½ĵæŶ
    0.10
    Activations Density 0.010%

    No Known Activations