© 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. 9928
    Prev
    Next
    INDEX
    Explanations

    minneapolis and minnesota places

    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»įåħ´
    -0.09
     ech
    -0.09
    æĭĤ
    -0.09
    èĩªèIJ¥
    -0.08
    çģ¼
    -0.08
     Georgia
    -0.08
    åı°å·ŀ
    -0.08
    azu
    -0.08
    çĭ®åŃIJ
    -0.08
    addon
    -0.08
    POSITIVE LOGITS
     Minnesota
    0.16
    Minnesota
    0.15
     Minneapolis
    0.13
    åIJīæŀĹçľģ
    0.12
    åIJīæŀĹ
    0.12
    æ´®
    0.12
    èĬ¬åħ°
    0.11
    åĵĪå°Ķ滨
    0.11
    Berry
    0.10
     Lutheran
    0.10
    Activations Density 0.070%

    No Known Activations