© 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. 10971
    Prev
    Next
    INDEX
    Explanations

    game 3 / third season / point

    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
    utes
    -0.23
    wend
    -0.20
     Buff
    -0.20
    plash
    -0.19
    Scaler
    -0.18
    ç§ĭåŃ£
    -0.18
    è½²
    -0.18
    hs
    -0.17
    abol
    -0.17
    æŀ¶åŃIJ
    -0.17
    POSITIVE LOGITS
    åĢ¡
    0.21
    getString
    0.20
    åĪ»
    0.19
     Aydın
    0.19
    è£ħå¤ĩåĪ¶éĢł
    0.19
    .sender
    0.18
     GLFW
    0.18
    Ñij
    0.18
    çĤ¹å¤ļ
    0.18
    emd
    0.18
    Activations Density 0.001%

    No Known Activations