© 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. 39075
    Prev
    Next
    INDEX
    Explanations

    linework, strokes, geometric

    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
    ä»ħä¾Ľ
    -0.10
    é¦Ķ
    -0.10
    ENA
    -0.09
    çĿ
    -0.09
    idy
    -0.09
    éĽİ
    -0.08
    èĤ´
    -0.08
    oogle
    -0.08
    çĿ¢
    -0.08
    EMA
    -0.08
    POSITIVE LOGITS
    çĹķ迹
    0.12
    çĹķ
    0.11
    ä¸Ģç¬Ķ
    0.11
     strokes
    0.10
    ç¬Ķ
    0.09
    ä¸ĢæĬ¹
    0.09
    线æĿ¡
    0.09
    éĽ¾
    0.09
    åĪ·
    0.09
    çķĻä¸ĭ
    0.09
    Activations Density 0.033%

    No Known Activations