© 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. 35212
    Prev
    Next
    INDEX
    Explanations

    Brendon or Brandon

    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
    ะ
    -0.11
    orta
    -0.10
    usal
    -0.10
    odos
    -0.09
    omorphic
    -0.09
    ikal
    -0.09
     Admir
    -0.09
    ters
    -0.09
    opsis
    -0.09
    .truth
    -0.09
    POSITIVE LOGITS
    عÙħÙĦ
    0.10
    igh
    0.09
    OrUpdate
    0.09
    иÑģк
    0.09
    è¹ĭ
    0.09
     gá»ijc
    0.08
    ç¥ķ
    0.08
    ÌĢ
    0.08
    椰
    0.08
    ummer
    0.08
    Activations Density 0.014%

    No Known Activations