© 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. 63656
    Prev
    Next
    INDEX
    Explanations

    redistribution and use

    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
    IZER
    -0.13
     иÑģполÑĮзование
    -0.11
    使çĶ¨èĢħ
    -0.10
    à¹Į
    -0.10
    sat
    -0.09
    ships
    -0.09
    çĶ¨èį¯
    -0.09
    çĶ¨æĿ¥
    -0.09
    theon
    -0.09
    _usage
    -0.09
    POSITIVE LOGITS
    fully
    0.17
    ful
    0.15
    fulness
    0.12
    able
    0.12
    è¿ĩçļĦ
    0.12
    lessly
    0.12
    FUL
    0.12
    full
    0.10
    cols
    0.10
    itarian
    0.10
    Activations Density 0.268%

    No Known Activations