© 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. 16771
    Prev
    Next
    INDEX
    Explanations

    shapechange or disguise

    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
    æį§
    -0.20
    帷
    -0.19
    ç¦ıå¾·
    -0.18
    秩åºı
    -0.18
    akk
    -0.18
    æı¡
    -0.18
    stops
    -0.17
    æŃī
    -0.17
     recess
    -0.17
    éĿ
    -0.17
    POSITIVE LOGITS
    åıĺæĪIJ
    0.26
    澡
    0.24
    åıĺå½¢
    0.23
    åıĺ为
    0.23
    åĮĸ
    0.23
    å½¢æĢģ
    0.22
     dạng
    0.20
    åıĺåĮĸ
    0.20
    åıĺæĪIJäºĨ
    0.20
    çĬ¶æĢģä¸ĭ
    0.20
    Activations Density 0.036%

    No Known Activations