© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-8B
    5. 18-RESID-BATCHTOPK-65K__L0-80
    7. 106
    Prev
    Next
    INDEX
    Explanations

    tic tac toe game boards

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-8b-saes/saes_Qwen_Qwen3-8B_batch_top_k/resid_post_layer_18
    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
    emean
    -0.27
    æµģæĺŁ
    -0.26
    TÄ°
    -0.26
    _calibration
    -0.24
    IPA
    -0.24
    .bias
    -0.24
     вÑĭпÑĥÑģк
    -0.24
     instrumentation
    -0.24
     averaged
    -0.24
    ãĥĶãĥ¼
    -0.23
    POSITIVE LOGITS
     grid
    0.60
    æ£ĭ
    0.53
    ç½ijæł¼
    0.52
     grids
    0.51
    grid
    0.48
     Grid
    0.46
     cells
    0.45
     blocks
    0.44
    åĽ´æ£ĭ
    0.43
    _grid
    0.43
    Activations Density 0.170%

    No Known Activations