© 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. 62075
    Prev
    Next
    INDEX
    Explanations

    minnesota, minneapolis, st. paul

    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
     Bermuda
    -0.09
    æľ¬å½ĵ
    -0.09
     implicit
    -0.08
     pres
    -0.08
    8
    -0.08
    ä¾ĭå¤ĸ
    -0.08
    ä¸ī峡
    -0.08
     des
    -0.08
    akis
    -0.08
    6
    -0.08
    POSITIVE LOGITS
    Minnesota
    0.16
     Minnesota
    0.15
     Minneapolis
    0.14
    æ²Īéĺ³
    0.13
    æ´®
    0.12
    åIJīæŀĹçľģ
    0.12
    åIJīæŀĹ
    0.11
     Svens
    0.11
    apolis
    0.10
     Dakota
    0.10
    Activations Density 0.079%

    No Known Activations