© 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. 27703
    Prev
    Next
    INDEX
    Explanations

    time indicators (am/pm)

    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
    åįĪé¤IJ
    -0.14
    é²ľæĺİ
    -0.11
     lunch
    -0.10
     noon
    -0.10
    åįĪåIJİ
    -0.10
    ä¸ĬåįĪ
    -0.10
    noon
    -0.09
     Rosenberg
    -0.09
    ä¸ŃåįĪ
    -0.09
     Trap
    -0.09
    POSITIVE LOGITS
    å¤ľ
    0.18
    æ·±å¤ľ
    0.16
     tonight
    0.16
    ä¹ĭå¤ľ
    0.14
    å¤ľéĹ´
    0.14
     nights
    0.14
    ä»ĬæĻļ
    0.14
     Äijêm
    0.13
    å¤ľæĻļ
    0.13
     Tonight
    0.13
    Activations Density 0.021%

    No Known Activations