© 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. 32012
    Prev
    Next
    INDEX
    Explanations

    US cities and states

    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
    西æ¹ĸ
    -0.11
     Hub
    -0.10
    大æĪĺ
    -0.10
    å¼Ģå°ģ
    -0.10
    ingly
    -0.08
    nyder
    -0.08
    ä¸įçĶ±
    -0.08
    ogn
    -0.08
    ë¡Ŀ
    -0.08
    Hub
    -0.08
    POSITIVE LOGITS
    æ³ī
    0.09
    æ³°å±±
    0.09
    çļĭ
    0.09
    å½Ŀ
    0.09
    Bindings
    0.09
    zzo
    0.09
    åıįæŃ£
    0.08
    åıį对
    0.08
    æķĿ
    0.08
     Appalachian
    0.08
    Activations Density 0.017%

    No Known Activations