© 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. 63000
    Prev
    Next
    INDEX
    Explanations

    figure studies

    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
    tractor
    -0.12
    大æĪ·
    -0.09
    yer
    -0.09
    åĭĥåĭĥ
    -0.09
    ë£Į
    -0.09
    -going
    -0.09
    ness
    -0.09
    à¸Ļาà¸Ļ
    -0.09
    edia
    -0.09
    engers
    -0.09
    POSITIVE LOGITS
    tte
    0.11
    åĿĽ
    0.10
    lec
    0.09
    istic
    0.09
    累累
    0.09
    head
    0.09
    лÑıÑĢ
    0.09
    gerald
    0.09
    heads
    0.09
    pus
    0.09
    Activations Density 0.028%

    No Known Activations