© 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. 62421
    Prev
    Next
    INDEX
    Explanations

    city 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
    d
    -0.08
    emos
    -0.08
    ä¸Ńåįİ
    -0.08
    estar
    -0.08
    Hist
    -0.08
    abble
    -0.07
    obot
    -0.07
    åľ°åŁŁ
    -0.07
     Hao
    -0.07
    å¤ļæĸ¹
    -0.07
    POSITIVE LOGITS
    iani
    0.09
    iard
    0.09
    è¯Ŀ
    0.08
    è¹ī
    0.08
    zug
    0.08
    xis
    0.08
    人åĬĽ
    0.08
    èµĶ
    0.08
    æĸ¹åľĨ
    0.08
    teen
    0.08
    Activations Density 0.080%

    No Known Activations