© 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. 15931
    Prev
    Next
    INDEX
    Explanations

    body organs and systems

    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
    符åIJĪ
    -0.23
    gger
    -0.20
    ez
    -0.20
    注æĦıåĪ°
    -0.20
    é¾ĭ
    -0.20
    åIJ¬å®Į
    -0.19
    Notifier
    -0.19
    ride
    -0.19
    æĭĨ
    -0.19
    æĶ»
    -0.19
    POSITIVE LOGITS
    éĿ¢ç§¯çº¦
    0.24
    æ¯ı天éĥ½
    0.23
    STA
    0.22
    ä¸įåģľåľ°
    0.20
    çļĦè§Ĵèī²
    0.20
    åįĹåĮĹ
    0.20
    ough
    0.20
     ROLE
    0.19
    è¡Į使
    0.19
    ä½Ī
    0.19
    Activations Density 0.102%

    No Known Activations