© 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. 4170
    Prev
    Next
    INDEX
    Explanations

    wipe out, eliminate, dispose

    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
    æ¸İ
    -0.10
    éªĤ
    -0.10
    éĴIJ
    -0.09
    кÑĤ
    -0.09
    ockey
    -0.09
    ç½µ
    -0.09
    vig
    -0.09
    æĮ¥
    -0.09
    SED
    -0.09
    зов
    -0.08
    POSITIVE LOGITS
    çģŃ
    0.13
    æ¶ĪçģŃ
    0.13
    ç«ŀäºī对æīĭ
    0.10
    æĹłå£°
    0.09
    åĩºå±Ģ
    0.09
     eliminate
    0.09
    dispose
    0.09
     dispos
    0.09
    çľ¨çľ¼
    0.09
    inish
    0.09
    Activations Density 0.050%

    No Known Activations