© 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. 35342
    Prev
    Next
    INDEX
    Explanations

    HTML document structure

    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
    ingly
    -0.10
    ksen
    -0.10
    stag
    -0.10
    rens
    -0.09
    ĩ
    -0.09
    PrototypeOf
    -0.09
    åݨ
    -0.09
    ement
    -0.09
    обÑĢаз
    -0.08
    lington
    -0.08
    POSITIVE LOGITS
    æµ·æ¹¾
    0.09
    ize
    0.08
    ting
    0.08
    uras
    0.08
    ized
    0.08
    ä¸Ģæľ¬ä¹¦
    0.08
    enton
    0.08
    ê°IJ
    0.08
    èĬ¥
    0.08
    useum
    0.08
    Activations Density 0.074%

    No Known Activations