© 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. 15629
    Prev
    Next
    INDEX
    Explanations

    codes like ij, eb, pt

    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
    çĿ¨
    -0.20
     nom
    -0.19
    ies
    -0.18
    ä¸Ģè´¯
    -0.18
    主義
    -0.18
    è¯Ń
    -0.18
    ulp
    -0.18
     PyErr
    -0.18
    eye
    -0.17
    ä¸Ĭä¸ĭ
    -0.17
    POSITIVE LOGITS
    女æľĭåıĭ
    0.22
    Binder
    0.21
    ç»ĨåĮĸ
    0.21
    èĸ¨
    0.21
    å¤ľéĹ´
    0.21
    é«ĺ峰论åĿĽ
    0.20
    uil
    0.19
    ëį°
    0.19
    å¤ĸå¥Ĺ
    0.19
    _reason
    0.18
    Activations Density 0.004%

    No Known Activations