© 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. 16808
    Prev
    Next
    INDEX
    Explanations

    primary sources materials documents

    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
    æ¦Ħ
    -0.21
    _ABORT
    -0.20
     pumps
    -0.20
     tjejer
    -0.19
    åıijå±ķçIJĨ念
    -0.19
    å¥ĭæĸĹ缮æłĩ
    -0.19
    ä¸İåħ¶
    -0.18
    æŃ£å¼ıåIJ¯åĬ¨
    -0.18
    éĴĿ
    -0.18
    åįĥéĩĮ
    -0.18
    POSITIVE LOGITS
    åı²æĸĻ
    0.28
    èµĦæĸĻ
    0.25
    æĿIJæĸĻ
    0.25
     materials
    0.24
     sources
    0.23
     documents
    0.23
    usty
    0.22
    åĨ·
    0.21
    çĶĦ
    0.21
    è§ģè¯ģ
    0.21
    Activations Density 0.017%

    No Known Activations