© 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. 38608
    Prev
    Next
    INDEX
    Explanations

    flavor and flavour

    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
    omi
    -0.10
    erval
    -0.09
    itate
    -0.09
    ainty
    -0.09
    ãģĵãģ¨ãģ«
    -0.09
    ees
    -0.09
    äºĨä¸Ģ个
    -0.09
    zelf
    -0.09
    ÙĪع
    -0.09
    ehler
    -0.08
    POSITIVE LOGITS
    åįģ足
    0.15
    åĻĮ
    0.13
    ably
    0.10
    åIJĦæł·
    0.10
    带头人
    0.10
    less
    0.10
    ç¾¤å²Ľ
    0.10
    鼷æĸ¯
    0.10
    ful
    0.09
    ģ
    0.09
    Activations Density 0.010%

    No Known Activations