© 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. 16288
    Prev
    Next
    INDEX
    Explanations

    King Kong

    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
    管çIJĨä¸Ńå¿ĥ
    -0.21
    SWG
    -0.20
    REW
    -0.19
    (dispatch
    -0.19
    ç¨Ĺ
    -0.18
    aight
    -0.18
    温馨
    -0.18
    赶赴
    -0.18
    ç¾İå¦Ļ
    -0.18
    Disconnected
    -0.18
    POSITIVE LOGITS
    尺度
    0.19
     Electoral
    0.19
    à¸Ħà¸Ń
    0.18
    å¸Ī
    0.18
    berg
    0.18
    ban
    0.18
    icle
    0.18
    éĢıæ°Ķ
    0.17
     espa
    0.17
     pick
    0.17
    Activations Density 0.001%

    No Known Activations