© 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. 2649
    Prev
    Next
    INDEX
    Explanations

    Black, Wahlberg, man, Black

    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
     Fern
    -0.09
    è§Ĭ
    -0.09
    离éĢĢä¼ij
    -0.09
    ossed
    -0.09
    é«ĺ楼
    -0.08
    ç¾İæ´²
    -0.08
    为空
    -0.08
    æ±²
    -0.08
    .Shapes
    -0.08
    åįĸ
    -0.08
    POSITIVE LOGITS
    å¹Į
    0.10
    ailure
    0.09
    åIJ¬åıĸ
    0.09
    Ñģел
    0.09
    etwork
    0.08
    è¾IJ
    0.08
    éĹ¾
    0.08
    详ç»Ĩä»ĭç»į
    0.08
    å®ŀä¹ł
    0.08
    çļĦ第ä¸Ģ
    0.08
    Activations Density 0.038%

    No Known Activations