© 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. 53394
    Prev
    Next
    INDEX
    Explanations

    attribute related programming concepts

    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
    æİĤ
    -0.10
    rie
    -0.10
    ï¸
    -0.09
    åºľ
    -0.09
    liness
    -0.09
    ç¨Ĺ
    -0.09
     dozen
    -0.09
    屿
    -0.09
    ongan
    -0.09
    -appointed
    -0.09
    POSITIVE LOGITS
    IBUT
    0.13
    TING
    0.11
    IBUTES
    0.11
    alogy
    0.09
    ively
    0.09
    __((
    0.09
    ials
    0.09
     blame
    0.09
    ivism
    0.09
    aceous
    0.08
    Activations Density 0.048%

    No Known Activations