© 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. 55231
    Prev
    Next
    INDEX
    Explanations

    welcome and positive service statements

    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
     khá»ıi
    -0.08
    顶
    -0.08
    æ¹¾åĮº
    -0.08
    ORK
    -0.07
    çĪµå£«
    -0.07
    ified
    -0.07
    æľī没æľī
    -0.07
    ä¸ĸ人
    -0.07
    statt
    -0.07
    触
    -0.07
    POSITIVE LOGITS
    åIJ¸å¼ķåĬĽ
    0.11
     ÑģÑĥммÑĥ
    0.10
    acob
    0.10
    为æĤ¨æıIJä¾Ľ
    0.10
    ç¬ķ
    0.10
    /respond
    0.10
    éķ¿å¾Ĺ
    0.09
    ç»ĻæĤ¨
    0.09
    ophage
    0.09
    åıĭ好
    0.09
    Activations Density 0.027%

    No Known Activations