© 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. 49838
    Prev
    Next
    INDEX
    Explanations

    top-level, top-notch, top-tier

    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
    hips
    -0.13
    hop
    -0.10
    说æĺ¯
    -0.10
    umin
    -0.09
    wen
    -0.09
    ãģıãĤĭ
    -0.09
    ingly
    -0.09
    å®Įæ¯ķ
    -0.09
    hip
    -0.09
    	TokenName
    -0.08
    POSITIVE LOGITS
    most
    0.18
    pling
    0.15
    -notch
    0.14
    ographical
    0.13
    ography
    0.12
    onym
    0.11
     ведÑĮ
    0.11
    orary
    0.11
    draft
    0.11
    -tier
    0.11
    Activations Density 0.069%

    No Known Activations