© 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. 54907
    Prev
    Next
    INDEX
    Explanations

    photon and light

    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
    æ¸ħæĺİ
    -0.09
    æµļ
    -0.09
    çľĭä»ĸ
    -0.08
    æĻĥ
    -0.08
    ä¾ĭè¡Į
    -0.08
     MVP
    -0.08
    躺çĿĢ
    -0.08
    æĿµ
    -0.08
    .US
    -0.08
     alm
    -0.08
    POSITIVE LOGITS
    å°Ħ
    0.09
    é¢ijçİĩ
    0.09
     TAR
    0.09
    æ¯Ķåĸ»
    0.09
    _FREQUENCY
    0.08
     tar
    0.08
     incident
    0.08
    çķĻ
    0.08
     Hein
    0.08
     Rosenstein
    0.08
    Activations Density 0.263%

    No Known Activations