© 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. 14527
    Prev
    Next
    INDEX
    Explanations

    risk, attack, meaning, search, gift

    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
    åħ¨æĸĩ
    -0.25
    两大
    -0.22
    nor
    -0.21
    isas
    -0.20
    çĶµç«Ļ
    -0.20
    太太
    -0.19
    åħ¨åijĺ
    -0.19
    å¤ļæķ°
    -0.19
    å¿«éĢŁå¢ŀéķ¿
    -0.19
    两类
    -0.18
    POSITIVE LOGITS
     perhaps
    0.25
     somehow
    0.23
    çŃīçŃī
    0.22
    èĢĮä¸įæĺ¯
    0.21
     maybe
    0.21
    çĶļèĩ³
    0.19
    Perhaps
    0.18
    ä¸ĢæŃ¥ä¸ĢæŃ¥
    0.18
    perhaps
    0.18
     perch
    0.18
    Activations Density 0.170%

    No Known Activations