© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 51370
    Prev
    Next
    INDEX
    Explanations

    pull back, scale down, bow out

    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
    alez
    -0.10
    侧
    -0.09
    åŁĭ
    -0.09
    æ¾Ī
    -0.09
    çļĦè¿ĽæŃ¥
    -0.09
    BED
    -0.08
    Ø®ÙĦ
    -0.08
    çĵł
    -0.08
    iker
    -0.08
    ä½ŀ
    -0.08
    POSITIVE LOGITS
    太快
    0.10
    ả
    0.09
    æ»ĩ
    0.09
    äºĨä¸Ģåľº
    0.09
    yro
    0.08
    .compat
    0.08
    oom
    0.08
    çķ¥æľī
    0.08
    -desc
    0.08
    _SCENE
    0.08
    Activations Density 0.013%

    No Known Activations