© 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. 11631
    Prev
    Next
    INDEX
    Explanations

    guide rail

    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
    imin
    -0.20
    obot
    -0.20
    coil
    -0.19
    æĻ®
    -0.18
    olor
    -0.17
    odom
    -0.17
    eurs
    -0.17
    isis
    -0.16
    anut
    -0.16
     Somehow
    -0.16
    POSITIVE LOGITS
    åĬĽè¿ĺæĺ¯
    0.21
    çijķ
    0.20
    å»ĵ
    0.20
    èį¯åĵģ
    0.19
    éŀį
    0.19
     ÐIJлекÑģан
    0.18
    åĨ°æ·ĩ
    0.18
    管çIJĨåĴĮ
    0.18
    ç»ıéªĮåĴĮ
    0.18
    容å¿į
    0.18
    Activations Density 0.348%

    No Known Activations