© 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. 58803
    Prev
    Next
    INDEX
    Explanations

    mythology and legends

    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
    çľĭä¸įåĪ°
    -0.09
    è£ħ
    -0.09
     Duck
    -0.08
    òa
    -0.08
     пен
    -0.08
    (FLAGS
    -0.08
    ãĥ¼ãĤ¿ãĥ¼
    -0.08
    éĻ¸
    -0.08
    anj
    -0.07
    STS
    -0.07
    POSITIVE LOGITS
    ä¼łè¯´
    0.15
     Legend
    0.12
     legend
    0.12
    Legend
    0.12
    ä¼łå¥ĩ
    0.12
    ç¥ŀè¯Ŀ
    0.11
    ä¼łéĹ»
    0.10
    çĽ¸ä¼ł
    0.10
     myth
    0.10
    辫
    0.10
    Activations Density 0.088%

    No Known Activations