© 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. 62321
    Prev
    Next
    INDEX
    Explanations

    field activities or locations

    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
    ampa
    -0.09
    çľ¼çļ®
    -0.09
    èĤ©
    -0.08
    çľ¼éĩĮ
    -0.08
    umber
    -0.08
    <small
    -0.08
    YP
    -0.08
    undi
    -0.08
    è¿IJ转
    -0.08
    dos
    -0.08
    POSITIVE LOGITS
    mares
    0.09
    legen
    0.09
    arshal
    0.09
    ignon
    0.09
    Insn
    0.09
    roller
    0.09
    alie
    0.09
    éªĬ
    0.08
    è¸Ł
    0.08
    каÑĤ
    0.08
    Activations Density 0.050%

    No Known Activations