© 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. 3921
    Prev
    Next
    INDEX
    Explanations

    process surveillance or procedure

    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
    åĬŁå¤«
    -0.11
    rey
    -0.10
    ÑĢаж
    -0.10
    Processor
    -0.09
    _processes
    -0.09
    iger
    -0.09
    ÑĢез
    -0.09
    æ¦ľ
    -0.09
    tors
    -0.09
    _processor
    -0.09
    POSITIVE LOGITS
    sing
    0.17
    ively
    0.15
    ors
    0.13
    ional
    0.13
    sed
    0.12
    urement
    0.12
    ual
    0.11
    EDURE
    0.11
    ually
    0.11
    ioned
    0.11
    Activations Density 0.108%

    No Known Activations