© 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. 11458
    Prev
    Next
    INDEX
    Explanations

    cross-country skiers, bishops, canoeists, swimmers, goalkeepers

    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
    é«ĺå±±
    -0.21
    icted
    -0.20
    ernote
    -0.19
    é«ĺéĢŁ
    -0.19
    SetActive
    -0.18
    èĩ³ä¸Ĭ
    -0.18
    advert
    -0.18
    ãĥIJãĥ©ãĥ³ãĤ¹
    -0.17
     ëĮĢíĨµ
    -0.17
    иÑĢÑĥÑİÑī
    -0.17
    POSITIVE LOGITS
    举
    0.20
    å·²æľī
    0.19
     vs
    0.19
    ç¯ĵ
    0.18
    仨
    0.18
     studs
    0.18
    DEC
    0.18
    举起
    0.17
    寻常
    0.17
    igators
    0.17
    Activations Density 0.163%

    No Known Activations