© 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. 16279
    Prev
    Next
    INDEX
    Explanations

    in place of

    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
    /TR
    -0.18
    æ©IJ
    -0.18
    _pal
    -0.17
    _MB
    -0.17
     slippery
    -0.17
    deck
    -0.17
    аÑĤÑĥÑĢ
    -0.16
     hoạch
    -0.16
    èł²
    -0.16
    _mock
    -0.16
    POSITIVE LOGITS
    ä¼łç»ŁçļĦ
    0.25
    ä¼łç»Ł
    0.22
    æŃ£å¸¸çļĦ
    0.21
     normal
    0.21
    åİŁæľ¬
    0.20
     traditional
    0.20
     replacements
    0.20
    æĽ¿ä»£
    0.20
    æŃ£å¸¸
    0.20
    åİŁæĿ¥çļĦ
    0.20
    Activations Density 0.040%

    No Known Activations