© 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. 39365
    Prev
    Next
    INDEX
    Explanations

    driving

    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
    æ®ĭ
    -0.09
    èĩªæĦ¿
    -0.09
    åĿIJ
    -0.08
    æijĶ
    -0.08
    顽强
    -0.08
     tel
    -0.08
    åİĦ
    -0.08
    ä¼°åĢ¼
    -0.08
     bid
    -0.08
    ç¾İ人
    -0.08
    POSITIVE LOGITS
    å®īåħ¨
    0.10
    大å®Ĺ
    0.10
    æ·ij
    0.10
    é«ĺéĢŁåħ¬è·¯
    0.10
    æ²ī
    0.10
    é«ĺéĢŁ
    0.09
    åįŁ
    0.09
     дол
    0.09
    _OW
    0.09
    åīį线
    0.09
    Activations Density 0.072%

    No Known Activations