© 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. 50297
    Prev
    Next
    INDEX
    Explanations

    proximity to

    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
    åĬ©éķ¿
    -0.11
    æ³±
    -0.10
    å¸IJ篷
    -0.10
    åıijåĬ¨
    -0.09
    æ§Ľ
    -0.09
    oulder
    -0.09
    åĽ½ç±į
    -0.09
    oga
    -0.09
    èī°
    -0.08
    archs
    -0.08
    POSITIVE LOGITS
    便åĪ©
    0.13
    è·Ŀ离
    0.13
    交éĢļ
    0.12
    çļĦè·Ŀ离
    0.12
    便æį·
    0.11
    éĿłè¿ij
    0.11
    便äºİ
    0.11
    è·ĿéĽ¢
    0.11
     proximity
    0.10
    æĸ¹ä¾¿
    0.10
    Activations Density 0.065%

    No Known Activations