© 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. 31973
    Prev
    Next
    INDEX
    Explanations

    maze and labyrinth structures

    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
    æĬ¬å¤´
    -0.11
    å¹³æĿ¿
    -0.09
    屯
    -0.09
    çijķ
    -0.09
    æįį
    -0.09
    éĴ¤
    -0.08
    è¾Ĩ
    -0.08
    ammen
    -0.08
    ä»°
    -0.08
    ç§Łè½¦
    -0.08
    POSITIVE LOGITS
    è¿·
    0.18
     maze
    0.14
    迷失
    0.13
    abyrinth
    0.12
     labyrinth
    0.12
     Maze
    0.12
    abyrin
    0.11
    åħ¥åı£
    0.11
    maze
    0.10
    诣
    0.10
    Activations Density 0.069%

    No Known Activations