© 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. 49732
    Prev
    Next
    INDEX
    Explanations

    track listing and credits

    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
    人家
    -0.10
    Mounted
    -0.09
    åĺ´
    -0.09
    elic
    -0.09
    æīĭå¥Ĺ
    -0.09
    åįĩ
    -0.08
    çļĭ
    -0.08
    .statusCode
    -0.08
    çĹĽ
    -0.08
    寿
    -0.08
    POSITIVE LOGITS
    Credits
    0.10
    credits
    0.09
     Credits
    0.09
    裨
    0.09
    å°ģ
    0.09
    åįı
    0.09
    -track
    0.09
    å®īæİĴ
    0.08
    autop
    0.08
     credits
    0.08
    Activations Density 0.224%

    No Known Activations