© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 36871
    Prev
    Next
    INDEX
    Explanations

    on restrictions

    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
    /Peak
    -0.09
    éģĹæ¼ı
    -0.09
    è¿ĺæľīä»Ģä¹Ī
    -0.09
    缺å°ij
    -0.09
    JOIN
    -0.08
    顽
    -0.08
     Benson
    -0.08
    åįıä¼ļä¼ļåijĺ
    -0.08
    è¡Įç¨ĭ
    -0.08
     Bender
    -0.08
    POSITIVE LOGITS
    åīįæıIJ
    0.14
    åīįæıIJæĺ¯
    0.13
     compens
    0.13
    éĻIJéĩı
    0.12
    ä¸įå½±åĵį
    0.12
    æħİéĩį
    0.12
    éĻIJ
    0.11
    éĻIJå®ļ
    0.11
    è°¨æħİ
    0.11
     compensate
    0.11
    Activations Density 0.167%

    No Known Activations