© 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. 55217
    Prev
    Next
    INDEX
    Explanations

    cycle, cycles, cycling

    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
    hör
    -0.10
    imators
    -0.10
    好åIJĹ
    -0.10
    åıĭåĸĦ
    -0.09
    оÑĢÑĤ
    -0.09
    ãĥģãĥ³
    -0.09
    ayo
    -0.09
    hor
    -0.09
    ä¸į容
    -0.09
     hor
    -0.09
    POSITIVE LOGITS
     cycle
    0.22
    cycle
    0.21
     Cycle
    0.21
    循çݯ
    0.19
    Cycle
    0.18
    _cycle
    0.17
    åij¨æľŁ
    0.17
     cycles
    0.17
    -cycle
    0.16
    è½®åĽŀ
    0.16
    Activations Density 0.090%

    No Known Activations