© 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. 26913
    Prev
    Next
    INDEX
    Explanations

    avoidable, preventable, easily diagnosed

    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
    ECH
    -0.09
    UCE
    -0.09
    -0.09
    ç´ł
    -0.08
    åĤ¨å¤ĩ
    -0.08
    ä¸įå½±åĵį
    -0.08
    ih
    -0.08
    饷
    -0.08
    è¦ģæĬĬ
    -0.08
     Klo
    -0.08
    POSITIVE LOGITS
    åıijçĶŁåľ¨
    0.11
    çļĦåıijçĶŁ
    0.11
    æĺ¯åı¯ä»¥
    0.10
    à¸Ŀ
    0.10
    å®Įåħ¨åı¯ä»¥
    0.10
    ä¸įè¿ľ
    0.10
    å°ijåIJĥ
    0.09
    ç«ĭ足
    0.09
    eel
    0.09
    abler
    0.09
    Activations Density 0.108%

    No Known Activations