© 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. 35227
    Prev
    Next
    INDEX
    Explanations

    piece or pieces

    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
    Ñĩик
    -0.12
    缧
    -0.10
    çĶµåĻ¨
    -0.10
    çĿ¹
    -0.10
    仪
    -0.09
    imum
    -0.09
    gable
    -0.09
     chÃŃ
    -0.09
    eva
    -0.09
    unc
    -0.09
    POSITIVE LOGITS
    è°Ĺ
    0.10
    pieces
    0.09
     Pieces
    0.08
    è°İè¨Ģ
    0.08
    åľº
    0.08
     pieces
    0.08
    æįķ
    0.08
    (piece
    0.08
    ToFront
    0.08
    .piece
    0.08
    Activations Density 0.018%

    No Known Activations