© 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. 31628
    Prev
    Next
    INDEX
    Explanations

    icons and graphical elements

    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
    åºĦ
    -0.09
    赶
    -0.09
    å§ĵ
    -0.08
    èİĬ
    -0.08
    abal
    -0.08
    fm
    -0.08
    é£İæݧ
    -0.08
    www
    -0.08
    itur
    -0.08
    æ¿Ł
    -0.08
    POSITIVE LOGITS
    /icons
    0.13
    åĽ¾æłĩ
    0.12
    .setIcon
    0.12
    符åı·
    0.12
    (icon
    0.11
    .icons
    0.11
     icons
    0.11
    æłĩè¯Ĩ
    0.11
    icons
    0.10
    setIcon
    0.10
    Activations Density 0.184%

    No Known Activations