© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 22008
    Prev
    Next
    INDEX
    Explanations

    place names parts like Alaska, Snohomish, Klickitat

    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
    oub
    -0.10
     Nile
    -0.09
    psilon
    -0.09
    积æŀģåıĤä¸İ
    -0.08
    æ¶Ī
    -0.08
    é«Ģ
    -0.08
    ç°ĭ
    -0.08
     ISO
    -0.08
    ISO
    -0.08
    æµ·åįĹ
    -0.08
    POSITIVE LOGITS
    æĭĻ
    0.11
    忤
    0.10
    夷
    0.10
    è¤Ĭ
    0.10
    èĬ±éĴ±
    0.10
    森æŀĹ
    0.09
    irement
    0.09
    oppers
    0.09
    æ·ĸ
    0.09
    ç±į
    0.09
    Activations Density 0.007%

    No Known Activations