© 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. 61681
    Prev
    Next
    INDEX
    Explanations

    indicates or indicates

    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
    ä¸Ģç³»åĪĹ
    -0.08
    åı¦ä¸Ģç§į
    -0.08
    å®ĥçļĦ
    -0.08
    æĪIJ为
    -0.08
    ÑģÑĤеÑĢ
    -0.08
    BitFields
    -0.08
     Morton
    -0.07
    SupportedContent
    -0.07
     WINAPI
    -0.07
    èĢģ大
    -0.07
    POSITIVE LOGITS
    并ä¸į代表
    0.12
    åĬĽæ±Ĥ
    0.11
     listed
    0.11
    ä¸į代表
    0.10
    æľīæŶ
    0.10
    ä»ħä¾ĽåıĤèĢĥ
    0.10
    注æĺİåĩºå¤Ħ
    0.10
    éĻ¤éĿŀ
    0.10
    Unless
    0.10
    /tiny
    0.09
    Activations Density 0.149%

    No Known Activations