© 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. 2055
    Prev
    Next
    INDEX
    Explanations

    out of

    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
    atat
    -0.09
    æĬĬä½ł
    -0.09
    åĩºéĻ¢
    -0.09
    /or
    -0.09
    anges
    -0.09
    对ä¸įèµ·
    -0.09
    çļĦä¸Ģ大
    -0.09
    ä¸Ńåħ³æĿij
    -0.09
    æĿ¥èĩª
    -0.09
    LPARAM
    -0.09
    POSITIVE LOGITS
    ters
    0.13
    wards
    0.12
    /out
    0.12
    èĩªèº«çļĦ
    0.10
    寻常
    0.10
    ta
    0.09
    laden
    0.09
    -going
    0.09
    going
    0.09
    gers
    0.09
    Activations Density 0.026%

    No Known Activations