© 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. 12978
    Prev
    Next
    INDEX
    Explanations

    prime number question

    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
    ÑĤал
    -0.20
    .persist
    -0.20
    alus
    -0.19
    íķij
    -0.19
     Greatest
    -0.17
    mal
    -0.17
     (?)
    -0.17
     Rc
    -0.17
    æĥľ
    -0.17
    matic
    -0.17
    POSITIVE LOGITS
    ä¸İåIJ¦
    0.57
    åIJ¦
    0.51
    æĺ¯åIJ¦åŃĺåľ¨
    0.33
     æĺ¯åIJ¦
    0.32
    æĺ¯åIJ¦
    0.31
    æĺ¯åIJ¦æľī
    0.31
    æľī没æľī
    0.30
     whether
    0.29
    ãģĭãģ©ãģĨãģĭ
    0.28
     ìŬ
    0.28
    Activations Density 0.474%

    No Known Activations