© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-8B
    5. 18-RESID-BATCHTOPK-65K__L0-80
    7. 499
    Prev
    Next
    INDEX
    Explanations

    coloring outside puzzles

    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
    horn
    -0.28
     horns
    -0.27
     horn
    -0.25
    lund
    -0.25
    æݪæĸ½
    -0.25
    å¾ĭ
    -0.25
     combust
    -0.24
     ÑĢож
    -0.24
    gas
    -0.24
    书记
    -0.24
    POSITIVE LOGITS
    ä¸Ģå¹ħ
    0.35
    åľ°åĽ¾
    0.31
     tiles
    0.31
     puzzles
    0.31
     puzzle
    0.30
     redraw
    0.30
    ç»ĺçĶ»
    0.30
    åĽ¾æ¡Ī
    0.29
    çļĦåľ°åĽ¾
    0.28
    å£ģçĶ»
    0.28
    Activations Density 0.009%

    No Known Activations