© 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. 11280
    Prev
    Next
    INDEX
    Explanations

    ZMAX, N9, polyol, VCP, ALCL

    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
    POSIT
    -0.18
    å¥ī
    -0.17
     lut
    -0.17
    .linspace
    -0.17
    RTOS
    -0.17
    eners
    -0.16
    ç»Ħç»ĩçĶŁæ´»
    -0.16
     volta
    -0.15
    _lt
    -0.15
    LayoutConstraint
    -0.15
    POSITIVE LOGITS
    çŁ¾
    0.19
    æľ¬èº«çļĦ
    0.18
    interopRequireDefault
    0.17
    å¾ĹäºĨ
    0.17
    馥
    0.16
    åľ°ä¸Ĭ
    0.16
    å¾ĹçĽĬ
    0.16
    çŃ¹
    0.16
    åĪ©çī©
    0.16
    åı¤æĢª
    0.16
    Activations Density 1.119%

    No Known Activations