© 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. 36369
    Prev
    Next
    INDEX
    Explanations

    composer, arranger, conductor

    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
     деÑĢ
    -0.10
    VID
    -0.09
    ä¸ĢéĿ¢
    -0.09
    竺
    -0.09
    inge
    -0.09
    eko
    -0.09
    èĥĮçĿĢ
    -0.08
    è´¨
    -0.08
    æīĵè¿Ľ
    -0.08
     кваÑĢÑĤиÑĢ
    -0.08
    POSITIVE LOGITS
    æ³¼
    0.11
    å¯Ħ
    0.10
    çıŃåŃIJ
    0.10
    åĬ¨åijĺ
    0.10
    _spell
    0.09
    èIJİ缩
    0.09
    å¾Ĺ天
    0.09
    æ·±æ¸Ĭ
    0.09
    æ¾Ħæ¸ħ
    0.09
    .mods
    0.09
    Activations Density 0.085%

    No Known Activations