© 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. 11182
    Prev
    Next
    INDEX
    Explanations

    body parts and exercise

    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
    èĵĸ
    -0.19
    åħ±å»º
    -0.19
    æ³ĵ
    -0.19
    baugh
    -0.19
    èĥ¼
    -0.18
     dime
    -0.18
    rollers
    -0.18
     Ink
    -0.18
    adia
    -0.17
    _rq
    -0.17
    POSITIVE LOGITS
    设æĸ½å»ºè®¾
    0.22
    elib
    0.19
    thead
    0.19
     ama
    0.18
    èľĢ
    0.18
     ned
    0.18
    nty
    0.18
    å«Įå¼ĥ
    0.17
    éģ£
    0.17
    .logged
    0.17
    Activations Density 0.159%

    No Known Activations