© 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. 23245
    Prev
    Next
    INDEX
    Explanations

    device or devices

    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
    ìį¨
    -0.09
    ed
    -0.09
    нÑĥ
    -0.09
    oon
    -0.09
    blings
    -0.09
    ning
    -0.08
    幡
    -0.08
    ferences
    -0.08
    isma
    -0.08
    åľ°å¸¦
    -0.08
    POSITIVE LOGITS
    =device
    0.10
    çļ¿
    0.10
    /method
    0.10
    ãģıãģł
    0.10
    ually
    0.10
    olumbia
    0.09
    gree
    0.09
    anner
    0.09
    ivity
    0.09
    /people
    0.09
    Activations Density 0.121%

    No Known Activations