© 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. 53541
    Prev
    Next
    INDEX
    Explanations

    post articles and types

    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
    ANCE
    -0.12
    rd
    -0.12
    -0.12
    atics
    -0.10
    /he
    -0.10
    è¿ĩæĪ·
    -0.09
    низ
    -0.09
    plist
    -0.09
    odule
    -0.09
    clist
    -0.09
    POSITIVE LOGITS
    erior
    0.17
    pone
    0.16
    gres
    0.16
    gresql
    0.16
    greSQL
    0.14
    ings
    0.12
    graduate
    0.12
    manship
    0.12
    ive
    0.11
    itory
    0.11
    Activations Density 0.096%

    No Known Activations