© 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. 27847
    Prev
    Next
    INDEX
    Explanations

    hybrid variations

    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
    ạng
    -0.09
    оÑĤоÑĢ
    -0.09
    ãģ¥
    -0.09
     reopened
    -0.09
    缸çĪ±
    -0.08
    áŀı
    -0.08
    ìĵ°
    -0.08
    éĵº
    -0.08
    _PROVID
    -0.08
     Garland
    -0.08
    POSITIVE LOGITS
    ä¹ĭä½ľ
    0.10
    线ä¸Ĭ线ä¸ĭ
    0.10
    SizeMode
    0.09
    éģ
    0.09
    åīįåIJİ
    0.09
    åįĹåĮĹ
    0.09
    åŀĽ
    0.09
    æīĵéĢł
    0.09
     approaches
    0.09
    ockey
    0.09
    Activations Density 0.037%

    No Known Activations