© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 8404
    Prev
    Next
    INDEX
    Explanations

    retreat and withdraw

    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
    çĦ¶æĺ¯
    -0.09
    волÑĮ
    -0.09
    èħĶ
    -0.09
    é½IJåħ¨
    -0.09
    teenth
    -0.08
    ÐŀÐĿ
    -0.08
    æł·çļĦ
    -0.08
    hift
    -0.08
    éĢıæ°Ķ
    -0.08
    coords
    -0.08
    POSITIVE LOGITS
    ippy
    0.10
    Ñĩив
    0.10
    zin
    0.10
    Fullscreen
    0.09
    ANNER
    0.09
    ively
    0.09
    olib
    0.09
    Performed
    0.09
    缪
    0.09
    ä¸Ĭå¹´
    0.09
    Activations Density 0.008%

    No Known Activations