© 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. 62052
    Prev
    Next
    INDEX
    Explanations

    DO NOT EDIT

    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
    æĹłæĦı
    -0.09
    ç¾Ĭæ¯Ľ
    -0.08
    人æĢ§
    -0.08
    åıĹéĻIJ
    -0.08
    rea
    -0.08
    Disp
    -0.08
    ç¡
    -0.08
    reator
    -0.08
    åĪ«çļĦ
    -0.08
    éĻįå¹ħ
    -0.07
    POSITIVE LOGITS
    dit
    0.10
    çīĪæĿĥå½Ĵ
    0.09
    gnu
    0.09
    ãĤ¬ãĤ¤
    0.09
    dale
    0.09
     Lind
    0.09
    èIJį
    0.09
    温馨
    0.09
    .dy
    0.08
    ä¸Ģ人
    0.08
    Activations Density 0.037%

    No Known Activations