© 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. 17028
    Prev
    Next
    INDEX
    Explanations

    killed by victims

    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
    è¿Ļå¥Ĺ
    -0.27
    éļį
    -0.19
    ç®´
    -0.18
     manuals
    -0.18
     пеÑĢвого
    -0.18
    ä¹Łä¸įæķ¢
    -0.17
    ä½¥
    -0.17
    第ä¸Ģéĥ¨
    -0.17
    acas
    -0.17
    ç¥ĸåħĪ
    -0.17
    POSITIVE LOGITS
    ä¸Ģè¡Į
    0.24
    èĥª
    0.21
    åIJįåįķ
    0.20
    оÑī
    0.19
    èĵĸ
    0.19
    ä¸Ģè§Ī
    0.19
    å¸ĪçĶŁ
    0.19
    spread
    0.18
    .xlsx
    0.18
    inos
    0.18
    Activations Density 0.014%

    No Known Activations