© 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. 11036
    Prev
    Next
    INDEX
    Explanations

    off-field

    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
    è¿ľæĻ¯
    -0.10
    ä¸ī代
    -0.09
    åį³ä½¿æĺ¯
    -0.09
    ç¼ĺ
    -0.09
    å¿ĥ缮
    -0.09
    è¿ĩ大
    -0.09
    éĺģ
    -0.09
    æľīæĿ¡ä»¶
    -0.09
    æ¸ħ
    -0.08
    atri
    -0.08
    POSITIVE LOGITS
    以å¤ĸ
    0.13
    ä¹ĭå¤ĸ
    0.11
    çİ°å®ŀçĶŁæ´»
    0.10
    趸
    0.09
    端æŃ£
    0.09
    OMET
    0.09
    inton
    0.09
    æĭĪ
    0.09
    ately
    0.08
    Administrator
    0.08
    Activations Density 0.038%

    No Known Activations