© 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. 39198
    Prev
    Next
    INDEX
    Explanations

    live with following words

    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
    MLS
    -0.09
    ëŀĮ
    -0.09
    ÑģÑĤавлен
    -0.09
    íĶ½
    -0.09
    quito
    -0.09
    weit
    -0.09
    æľīåĬĽ
    -0.09
    ULA
    -0.09
    htub
    -0.09
     Sized
    -0.08
    POSITIVE LOGITS
    å¹³çŃī
    0.09
     Tir
    0.09
    out
    0.09
    ç¼ĩ
    0.09
    åºıå¹ķ
    0.08
    çļĵ
    0.08
    æĿijæ°ij们
    0.08
    uti
    0.08
    vat
    0.08
    utr
    0.08
    Activations Density 0.024%

    No Known Activations