© 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. 14332
    Prev
    Next
    INDEX
    Explanations

    holding something

    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
    eer
    -0.20
    oola
    -0.18
    HEME
    -0.18
    rous
    -0.18
    _SKIP
    -0.17
    odcast
    -0.17
    ä¹ŁçŁ¥éģĵ
    -0.17
    endcode
    -0.17
    eting
    -0.17
    -0.16
    POSITIVE LOGITS
    ä½ıäºĨ
    0.33
    ä¸įä½ı
    0.29
    ä½ı
    0.26
    åĬĽåº¦
    0.23
    ä¸į解
    0.20
    æīĭèĦļ
    0.18
    强度
    0.18
    ä¸įåĪ°
    0.18
    mates
    0.17
    å¾Ĺä½ı
    0.17
    Activations Density 0.019%

    No Known Activations