© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-14B
    5. 20-RESID-BATCHTOPK-65K__L0-80
    7. 17043
    Prev
    Next
    INDEX
    Explanations

    risk factors, filings, tests, background, Q&A, dates

    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
    éĢ¢
    -0.20
    emer
    -0.19
    æģ©
    -0.18
    çķĻæĦı
    -0.18
    thal
    -0.18
    ä¸ĢèĦļ
    -0.17
    æĬĬèĩªå·±
    -0.17
    каÑĤ
    -0.17
    åij
    -0.17
     Technician
    -0.17
    POSITIVE LOGITS
    Ø·
    0.21
    FIX
    0.20
    grav
    0.20
    åĨħéĥ¨æݧåĪ¶
    0.18
    éľľ
    0.18
    DIG
    0.18
    寻æ±Ĥ
    0.18
     yahoo
    0.18
     Franken
    0.18
    _FACT
    0.18
    Activations Density 0.001%

    No Known Activations