© 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. 10778
    Prev
    Next
    INDEX
    Explanations

    possibly desire or need

    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
    横
    -0.10
    ROUTE
    -0.09
    à¤Ĩ
    -0.08
    골
    -0.08
    æĥĨ
    -0.08
    omic
    -0.08
     Puzzle
    -0.08
    缸å½ĵäºİ
    -0.08
    _rs
    -0.08
    éĩijåŃĹ
    -0.08
    POSITIVE LOGITS
    å£ģåŀĴ
    0.11
    幸
    0.09
    éªĭ
    0.09
     possibly
    0.09
    è¯īæ±Ĥ
    0.09
    æīĢèĥ½
    0.09
    èĮ§
    0.09
    æı´
    0.09
    åı¯èĥ½åĩºçİ°
    0.09
    ä¹ĭæīĢ
    0.09
    Activations Density 0.032%

    No Known Activations