© 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. 34159
    Prev
    Next
    INDEX
    Explanations

    sequence of steps

    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
    nex
    -0.09
    æĽ
    -0.09
    橱
    -0.09
     ÑĢаÑģÑĤвоÑĢ
    -0.08
    ÄĦ
    -0.08
    åĪĽæĸ°åĪĽä¸ļ
    -0.08
    Git
    -0.08
     ÑģвÑıзи
    -0.08
     Pier
    -0.08
    å»ĵ
    -0.08
    POSITIVE LOGITS
    æŃ¥éª¤
    0.30
     steps
    0.27
     step
    0.23
    steps
    0.21
    ä¸ĢæŃ¥
    0.20
    _steps
    0.19
     Steps
    0.19
    第ä¸ĢæŃ¥
    0.19
     ÑĪаг
    0.18
    Steps
    0.17
    Activations Density 0.053%

    No Known Activations