© 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. 5641
    Prev
    Next
    INDEX
    Explanations

    names starting with G

    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
    uki
    -0.11
    fulness
    -0.11
    uka
    -0.10
    iqu
    -0.10
    GAME
    -0.09
    人éĥ½
    -0.09
    agram
    -0.09
    ikel
    -0.09
    ches
    -0.09
    pany
    -0.09
    POSITIVE LOGITS
    ging
    0.26
    ged
    0.18
    hetto
    0.17
    gable
    0.16
    GING
    0.16
    lobal
    0.15
    roup
    0.15
    gie
    0.15
    gers
    0.14
    redient
    0.14
    Activations Density 1.090%

    No Known Activations