© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 22374
    Prev
    Next
    INDEX
    Explanations

    frequency of updates or changes

    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
    潸
    -0.11
    æ¯Ļ
    -0.10
    íĥĿ
    -0.10
    errick
    -0.10
    åľĨ满
    -0.10
    交éĻħ
    -0.10
     Bran
    -0.10
    anford
    -0.09
    éĻĤ
    -0.09
     вли
    -0.09
    POSITIVE LOGITS
    æĽ´æĸ°
    0.23
     updates
    0.17
     update
    0.17
     æĽ´æĸ°
    0.16
     updating
    0.16
    update
    0.15
    Update
    0.14
     Update
    0.14
     UPDATE
    0.14
    -update
    0.14
    Activations Density 0.113%

    No Known Activations