© 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. 17469
    Prev
    Next
    INDEX
    Explanations

    vampire or vampires

    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
    ä¸įèµ·
    -0.12
    quo
    -0.10
    ilet
    -0.09
    人æ°ij
    -0.09
    éĿŀåĩ¡
    -0.09
    ough
    -0.09
     Salisbury
    -0.09
    led
    -0.09
    shore
    -0.09
    ings
    -0.09
    POSITIVE LOGITS
    æł·
    0.10
    è¡Įéķ¿
    0.09
    ä¸Ńéĵģ
    0.08
     кÑĢови
    0.08
    ically
    0.08
    ä¹ĭ乡
    0.08
    æĽľ
    0.08
     Ves
    0.08
    ye
    0.08
    cow
    0.08
    Activations Density 0.007%

    No Known Activations