© 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. 35499
    Prev
    Next
    INDEX
    Explanations

    city and town names

    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
    们
    -0.11
    oi
    -0.10
    åħ¬è®¤çļĦ
    -0.09
    _SID
    -0.09
    .cuda
    -0.09
    è®¤çľŁ
    -0.08
    agraph
    -0.08
    éŁ³
    -0.08
    oro
    -0.08
     rum
    -0.08
    POSITIVE LOGITS
    arity
    0.09
    妫
    0.09
    borough
    0.08
    idth
    0.08
    伸æīĭ
    0.08
    è¿İ
    0.08
    大çīĩ
    0.08
    åķ¼
    0.08
    å¥ij
    0.08
     Fuller
    0.08
    Activations Density 0.001%

    No Known Activations