© 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. 57099
    Prev
    Next
    INDEX
    Explanations

    working out issues

    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
    寸
    -0.10
    æĭ¿äºĨ
    -0.09
    екÑģ
    -0.09
    -defense
    -0.09
    HAL
    -0.08
    otts
    -0.08
    äººæł¼
    -0.08
    æ¦ľ
    -0.08
    åĬłæĭ¿å¤§
    -0.08
     HAL
    -0.08
    POSITIVE LOGITS
    лÑij
    0.09
    ÙħÙĬÙĦ
    0.09
    ucci
    0.09
    å¸ĥ
    0.09
    dam
    0.08
     Gat
    0.08
    Night
    0.08
    æŀľ
    0.08
    leh
    0.08
    æ¹ĺ西
    0.08
    Activations Density 1.233%

    No Known Activations