© 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. 32039
    Prev
    Next
    INDEX
    Explanations

    decide on

    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
    并ä¸įå¤ļ
    -0.10
    éĺį
    -0.09
    梳
    -0.09
    çIJĨ解åĴĮ
    -0.09
    /sites
    -0.09
    纺
    -0.08
    缴è¨Ģ
    -0.08
    rug
    -0.08
     cartel
    -0.08
    æ¯ĽåŃĶ
    -0.08
    POSITIVE LOGITS
    ç¹ģ
    0.11
    ajs
    0.09
    满æĦıçļĦ
    0.09
    å®ļäºĨ
    0.08
     tir
    0.08
    åĸĿèĮ¶
    0.08
    è¦ģä¸įè¦ģ
    0.08
    .nl
    0.08
     меÑĢ
    0.08
    NAL
    0.08
    Activations Density 0.021%

    No Known Activations