© 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. 31035
    Prev
    Next
    INDEX
    Explanations

    storage size units (GB, MB, B)

    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
    æµ·åı£
    -0.09
    Bootstrap
    -0.09
    .&
    -0.08
    楼
    -0.08
    éĥ¨å§Ķ
    -0.08
    поÑĤ
    -0.08
    inen
    -0.08
    Implementation
    -0.08
    (ele
    -0.08
    宿
    -0.08
    POSITIVE LOGITS
    angers
    0.10
    ioc
    0.10
    å¤ļå°ij
    0.09
    pls
    0.09
    éĥ½æĥ³
    0.09
    è·¯ç¨ĭ
    0.08
    nob
    0.08
    è°ĥåĬ¨
    0.08
    asto
    0.08
    å·¥ç¨ĭ
    0.08
    Activations Density 0.015%

    No Known Activations