© 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. 62191
    Prev
    Next
    INDEX
    Explanations

    update a table, image, or database

    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
    浪费
    -0.11
    /ss
    -0.10
    éĶı
    -0.09
    äºĨä¸Ģåľº
    -0.09
    åħīæ»ij
    -0.09
    andom
    -0.09
    ä¸į解
    -0.09
    纱
    -0.09
    å¤Ń
    -0.09
    ç¼¥
    -0.09
    POSITIVE LOGITS
    æĽ´æĸ°
    0.13
     æĽ´æĸ°
    0.12
    (update
    0.12
     Updating
    0.11
    /update
    0.10
    ä¸İæĹ¶ä¿±è¿Ľ
    0.10
    Updating
    0.10
    æ´²
    0.10
    updating
    0.10
    .update
    0.10
    Activations Density 0.153%

    No Known Activations