© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 8092
    Prev
    Next
    INDEX
    Explanations

    problem or solution

    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
    iat
    -0.09
    è°´
    -0.09
    éģ£
    -0.09
    edes
    -0.09
    lessons
    -0.08
    auer
    -0.08
     Unc
    -0.08
    æIJŀç¬ij
    -0.08
    edy
    -0.08
    abit
    -0.08
    POSITIVE LOGITS
     пÑĢоблемÑĭ
    0.14
    ä¹ĭéģĵ
    0.14
    (solution
    0.11
     solutions
    0.11
    è¿ĻäºĽéĹ®é¢ĺ
    0.11
    è¿Ļ个éĹ®é¢ĺ
    0.10
    解åĨ³æĸ¹æ¡Ī
    0.10
     Solutions
    0.10
    ì±ħ
    0.10
    çªģåĩºéĹ®é¢ĺ
    0.10
    Activations Density 0.081%

    No Known Activations