© 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. 11731
    Prev
    Next
    INDEX
    Explanations

    sports positions

    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
    çķ¥æľī
    -0.19
    åıĪèĥ½
    -0.17
    说çĿĢ
    -0.17
    initely
    -0.17
    _PADDING
    -0.17
    æĪij们ä¼ļ
    -0.17
    æĪij们åı¯ä»¥
    -0.17
    ç¨įå¾®
    -0.17
    åĵij
    -0.17
     convers
    -0.17
    POSITIVE LOGITS
    (simp
    0.20
    olic
    0.19
    çİ»çĴĥ
    0.18
    æµģæĺŁ
    0.18
     Cla
    0.18
    å§Ķ
    0.18
    ä¹ĭæĺŁ
    0.18
    Absent
    0.18
    éĺĶ
    0.18
    æĥ¯
    0.17
    Activations Density 0.042%

    No Known Activations