© 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. 5417
    Prev
    Next
    INDEX
    Explanations

    PlayStation products and 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
    èĪĮå°ĸ
    -0.08
    usc
    -0.08
    è´«åĽ°äººåı£
    -0.08
    ä¸Ģç»Ħ
    -0.08
    樱
    -0.08
    igt
    -0.08
    foil
    -0.08
    ç®ķ
    -0.08
     Wrestle
    -0.08
    å»ĸ
    -0.08
    POSITIVE LOGITS
    lint
    0.09
    .Features
    0.09
    æĩĪ
    0.09
    浦
    0.09
    _HEAP
    0.09
    suming
    0.08
    ANTE
    0.08
    rud
    0.08
    è®®
    0.08
    dex
    0.08
    Activations Density 0.012%

    No Known Activations