© 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. 61713
    Prev
    Next
    INDEX
    Explanations

    electoral district

    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
    ç¥ŀç§ĺ
    -0.09
    _extract
    -0.09
    æĪ·åı£
    -0.09
    æ¹Ķ
    -0.09
    _scaling
    -0.08
     ((__
    -0.08
    itest
    -0.08
    istra
    -0.08
    kdir
    -0.08
    çĤ¸
    -0.08
    POSITIVE LOGITS
    é³Ħ
    0.10
    abo
    0.09
    èĶ¬
    0.08
    é¦Ĵ头
    0.08
    clo
    0.08
    MBER
    0.08
    é³Ŀ
    0.08
    ä¹ĭäºī
    0.08
    ÑĢеÑģ
    0.08
     dolphin
    0.08
    Activations Density 0.017%

    No Known Activations