© 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. 23313
    Prev
    Next
    INDEX
    Explanations

    asking questions

    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
    æĥł
    -0.09
    è´¥
    -0.09
    éĻĭ
    -0.09
    没
    -0.09
    ured
    -0.09
    裹
    -0.08
     Mort
    -0.08
     оÑĤкÑĢ
    -0.08
    ï¸
    -0.08
    stress
    -0.08
    POSITIVE LOGITS
    è¿Ľä¸ĢæŃ¥
    0.10
    éĢ²ä¸ĢæŃ¥
    0.09
     further
    0.09
    åı¦æľī
    0.09
     далÑĮн
    0.09
    æľīä»»ä½ķ
    0.09
     Mell
    0.09
    ä¸İä¼Ĺä¸įåIJĮ
    0.09
     intended
    0.09
    棣
    0.08
    Activations Density 0.009%

    No Known Activations