© 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. 27895
    Prev
    Next
    INDEX
    Explanations

    rights reserved

    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
    rastructure
    -0.16
    DataGridViewTextBoxColumn
    -0.11
    htable
    -0.10
    dın
    -0.10
    å¾Ī好
    -0.10
    yclerView
    -0.10
    thern
    -0.09
    viously
    -0.09
    æĽ´å¥½
    -0.09
    第ä¸Ģå±Ĭ
    -0.09
    POSITIVE LOGITS
    orem
    0.24
    /Set
    0.11
    oretical
    0.11
    ä¹İ
    0.10
    ÑīиÑĤ
    0.10
    ндекÑģ
    0.10
    /Sub
    0.10
    -Line
    0.10
    notated
    0.09
    ories
    0.09
    Activations Density 7.608%

    No Known Activations