© 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. 39069
    Prev
    Next
    INDEX
    Explanations

    video footage

    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
    alian
    -0.09
    ilater
    -0.09
    idy
    -0.09
    _HS
    -0.09
    omal
    -0.09
    UBE
    -0.09
    iker
    -0.09
    utom
    -0.09
    tas
    -0.09
    iders
    -0.09
    POSITIVE LOGITS
     video
    0.11
    è§Ĩé¢ij
    0.11
    video
    0.11
    è§Ĥçľĭ
    0.10
     Video
    0.10
     streaming
    0.10
    _video
    0.09
    æĪĺçķ¥
    0.09
    Watching
    0.09
     Vimeo
    0.09
    Activations Density 0.189%

    No Known Activations