© 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. 58164
    Prev
    Next
    INDEX
    Explanations

    ramping up, gearing up, crank out

    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
    æĭį
    -0.10
    .timestamps
    -0.09
    è¶ģçĿĢ
    -0.09
     elev
    -0.09
     Chore
    -0.09
    æ¦ī
    -0.08
    åķĨæĪ·
    -0.08
    _DUMP
    -0.08
    imore
    -0.08
    ohl
    -0.08
    POSITIVE LOGITS
    è¿IJ转
    0.15
     gears
    0.11
    è¿IJä½ľ
    0.11
     gear
    0.10
    åĬ¨åĬĽ
    0.10
    驶
    0.09
    ạy
    0.08
    Fantastic
    0.08
     prime
    0.08
     Hav
    0.08
    Activations Density 0.031%

    No Known Activations