© 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. 11428
    Prev
    Next
    INDEX
    Explanations

    about, on, like, by, at

    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
    rot
    -0.09
    SError
    -0.09
    eer
    -0.09
    çīĮåŃIJ
    -0.08
    ÙĬÙĥ
    -0.08
    oen
    -0.08
    çĿĢæĢ¥
    -0.08
    æĢ»ä½ĵ
    -0.08
     unanimously
    -0.08
     leveled
    -0.08
    POSITIVE LOGITS
    æ¯į
    0.09
    comb
    0.09
    ä¸Ģåı¥è¯Ŀ
    0.09
    éĹ»åIJį
    0.09
    ราว
    0.09
    -than
    0.09
    clamation
    0.09
    elay
    0.08
    ä¸ĢæŃ¥
    0.08
    lays
    0.08
    Activations Density 0.030%

    No Known Activations