© 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. 11594
    Prev
    Next
    INDEX
    Explanations

    blade parts or aerodynamics

    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
    çıł
    -0.12
     knot
    -0.09
     CR
    -0.08
    çıłæ±Ł
    -0.08
    izen
    -0.08
    ä¸įåIJĪçIJĨ
    -0.08
     KL
    -0.08
    榴
    -0.08
    é¦ĸå¸Ń
    -0.08
    åīįæīĢ
    -0.08
    POSITIVE LOGITS
     wings
    0.17
    ç¿ħèĨĢ
    0.16
    åı¶çīĩ
    0.15
     Wings
    0.14
    -wing
    0.13
     wing
    0.13
    翼
    0.12
    ç¾½æ¯Ľ
    0.11
    wing
    0.11
    åı¶åŃIJ
    0.11
    Activations Density 0.087%

    No Known Activations