© 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. 18685
    Prev
    Next
    INDEX
    Explanations

    food items and food descriptions

    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
    æĵ¢
    -0.10
    è¢«åĽ°
    -0.09
    olec
    -0.09
    eti
    -0.09
     Rage
    -0.09
    åĺī
    -0.09
    åĸŁ
    -0.09
    .experimental
    -0.09
    .GetHashCode
    -0.08
    åı¯ä¾Ľ
    -0.08
    POSITIVE LOGITS
    éĢļ常æĺ¯
    0.12
    usually
    0.10
    è¦ģä¹Ī
    0.10
    éĢļ常
    0.10
    å½ĵåľ°äºº
    0.09
    ç¬ŀ
    0.09
    alu
    0.09
     usually
    0.09
    é¦ı
    0.09
    FG
    0.09
    Activations Density 0.092%

    No Known Activations