© 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. 63721
    Prev
    Next
    INDEX
    Explanations

    workouts and strength exercises

    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
    panic
    -0.12
    è´´
    -0.10
    rame
    -0.10
    pulse
    -0.09
    ÂŃi
    -0.09
    åĩłæŃ¥
    -0.09
    åIJ¬ä¼Ĺ
    -0.09
    笥
    -0.09
    èĦī
    -0.09
     pulse
    -0.09
    POSITIVE LOGITS
    ä¹Łè¦ģ
    0.09
    è¾ħåĬ©
    0.08
    æĮªå¨ģ
    0.08
    äºŃ
    0.08
     fern
    0.08
    å°±è¿ij
    0.08
    æ°ijæĹıæĸĩåĮĸ
    0.08
    afka
    0.07
    帽
    0.07
    让èĩªå·±
    0.07
    Activations Density 0.083%

    No Known Activations