© 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. 15959
    Prev
    Next
    INDEX
    Explanations

    P followed by punctuation or specific characters

    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
    å«ĸ
    -0.20
    iy
    -0.19
    uary
    -0.19
    æīĵéĢł
    -0.18
    被èªī
    -0.18
    vla
    -0.18
    æīįè¡Į
    -0.18
    ä¹Łåıªèĥ½
    -0.17
     Thousand
    -0.17
    ä¸Ģå¿ĥ
    -0.17
    POSITIVE LOGITS
    _cycles
    0.22
    æİİ
    0.20
    åİ¥
    0.20
    æł¸å¿ĥæĬĢæľ¯
    0.19
    èİ«åIJį
    0.19
    个交æĺĵ
    0.19
     gridColumn
    0.19
    зав
    0.18
    auce
    0.18
    æľĢåIJİä¸Ģ
    0.18
    Activations Density 0.007%

    No Known Activations