© 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. 35039
    Prev
    Next
    INDEX
    Explanations

    volunteer services

    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
    ä¸į认è¯Ĩ
    -0.09
    aph
    -0.09
    ç¼ħ
    -0.09
     Burnett
    -0.09
    çĶŁçī©ç§ijæĬĢ
    -0.08
    pha
    -0.08
    CHK
    -0.08
    躲éģ¿
    -0.08
    顾èĻij
    -0.08
    ria
    -0.08
    POSITIVE LOGITS
    å¿ĹæĦ¿
    0.17
    (vol
    0.16
    å¿ĹæĦ¿èĢħ
    0.14
     volunteers
    0.14
    èĩªæĦ¿
    0.13
     volunt
    0.13
    å¿ĹæĦ¿æľįåĬ¡
    0.13
    .vol
    0.12
     volunte
    0.12
     volunteer
    0.12
    Activations Density 0.027%

    No Known Activations