© 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. 60976
    Prev
    Next
    INDEX
    Explanations

    universities and libraries

    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
    å·¥ä½ľä¸Ń
    -0.09
     Hanna
    -0.09
    liqu
    -0.09
    ä¸Ĭå²Ĺ
    -0.08
    lep
    -0.08
    âm
    -0.08
    jective
    -0.08
    æk
    -0.08
    ody
    -0.08
    åĴķ
    -0.08
    POSITIVE LOGITS
    åĽ¾ä¹¦é¦Ĩ
    0.11
    .edu
    0.11
    åīį身
    0.10
    éĻĦå±ŀ
    0.10
    åħļå§Ķ书记
    0.10
    -aff
    0.10
    åŁĥå°Ķ
    0.10
     Libraries
    0.09
     campuses
    0.09
    libraries
    0.09
    Activations Density 0.123%

    No Known Activations