© 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. 6398
    Prev
    Next
    INDEX
    Explanations

    edit, editing, editor

    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
    anja
    -0.09
    marvin
    -0.09
    wend
    -0.09
    ìļ°
    -0.09
    èĻ¹
    -0.09
    ãĥķãĤ¡ãĥ³
    -0.08
    ceu
    -0.08
    avern
    -0.08
    è°
    -0.08
    ework
    -0.08
    POSITIVE LOGITS
    ç¼ĸè¾ij
    0.15
     Editing
    0.13
    (Edit
    0.13
    (edit
    0.12
    (editor
    0.11
     edit
    0.11
    .Editor
    0.11
    .edit
    0.11
    editing
    0.11
    .editor
    0.10
    Activations Density 0.210%

    No Known Activations