© 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. 16533
    Prev
    Next
    INDEX
    Explanations

    computerized control

    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
    -Ta
    -0.20
    avel
    -0.20
    è¿Ļæīįæĺ¯
    -0.19
    благо
    -0.19
    /google
    -0.18
    INGTON
    -0.18
     Aren
    -0.17
    ä¸įæĸŃåľ°
    -0.17
    æ·±åıĹ
    -0.17
    evin
    -0.17
    POSITIVE LOGITS
    icy
    0.22
    .getClassName
    0.19
    å·²ä¹ħçļĦ
    0.18
    ++]
    0.18
    )test
    0.17
    или
    0.17
    Ahead
    0.17
     Aug
    0.17
    æľīæŶ
    0.17
    ”çļĦ
    0.17
    Activations Density 0.186%

    No Known Activations