© 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. 63291
    Prev
    Next
    INDEX
    Explanations

    evaluating alternatives and options

    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
    çİĦ
    -0.11
    å¿Ŀ
    -0.09
    ä¹ĸ
    -0.09
    é¨Ļ
    -0.09
    æijģ
    -0.08
    ä¹±
    -0.08
    endDate
    -0.08
    cue
    -0.08
     Deaths
    -0.08
    åIJĥå¾Ĺ
    -0.08
    POSITIVE LOGITS
    éĢī项
    0.16
     alternatives
    0.15
    æĸ¹æ¡Ī
    0.15
     options
    0.14
    设计æĸ¹æ¡Ī
    0.13
     alternative
    0.13
     option
    0.13
     Options
    0.12
    æĥħæĻ¯
    0.12
    alternative
    0.11
    Activations Density 0.054%

    No Known Activations