© 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. Qwen3-14B
    5. 20-RESID-BATCHTOPK-65K__L0-80
    7. 11376
    Prev
    Next
    INDEX
    Explanations

    duration, lifespan, durability

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-14b-saes/saes_Qwen_Qwen3-14B_batch_top_k/resid_post_layer_20
    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
    ä¸ĢåĿĹ
    -0.21
    éĿ¢ç§¯
    -0.20
    çĶ¨èĩªå·±çļĦ
    -0.20
    æµĵ
    -0.20
    çĽĸ
    -0.19
    ä¸įå¾Ĺå·²
    -0.19
    èĵĭ
    -0.19
    -pad
    -0.19
    responsive
    -0.19
    emia
    -0.19
    POSITIVE LOGITS
    寿åij½
    0.23
    frey
    0.21
    使çĶ¨å¯¿åij½
    0.20
     helicopt
    0.19
    roys
    0.19
     Warranty
    0.19
    _putchar
    0.19
     годÑĭ
    0.19
    horn
    0.18
    rxjs
    0.18
    Activations Density 0.032%

    No Known Activations