© 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. 57277
    Prev
    Next
    INDEX
    Explanations

    design

    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
    å¥īçĮ®
    -0.09
    享åıĹåĪ°
    -0.09
    æĹłç§ģ
    -0.08
     kne
    -0.08
    çĶĺ
    -0.08
    è¹²
    -0.08
    åĶ¯
    -0.08
    è´¡
    -0.08
     bottoms
    -0.08
    Fat
    -0.08
    POSITIVE LOGITS
    å¤ĸå½¢
    0.14
    å¤ĸè§Ĥ
    0.14
    è½®å»ĵ
    0.13
    线æĿ¡
    0.12
    å¡ijéĢł
    0.11
    设计çIJĨ念
    0.11
    éĢłåŀĭ
    0.10
     tasarım
    0.10
    ãĥĩãĤ¶ãĤ¤ãĥ³
    0.09
    éĽķå¡ij
    0.09
    Activations Density 0.210%

    No Known Activations