© 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. 55464
    Prev
    Next
    INDEX
    Explanations

    from a place

    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
    èĩªåľ¨
    -0.11
    æīĢæľī人
    -0.09
    èĩªå¦Ĥ
    -0.09
     Ñģеб
    -0.08
    _PTR
    -0.08
    奥è¿IJ
    -0.08
    æĿ¥èĩª
    -0.08
    çŃĽ
    -0.08
    ingen
    -0.08
     OST
    -0.08
    POSITIVE LOGITS
    åħ¨åĽ½åIJĦåľ°
    0.10
    éħįå¥Ĺ设æĸ½
    0.09
    çĸĻ
    0.09
     sliders
    0.08
    AGER
    0.08
    maf
    0.08
    æĹı
    0.08
    gra
    0.08
    åIJĦè¡ĮåIJĦ
    0.08
     ÙĬستطÙĬع
    0.08
    Activations Density 0.046%

    No Known Activations