© 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. 16369
    Prev
    Next
    INDEX
    Explanations

    variable capacitor devices

    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
    å¾Ĺ天
    -0.19
    亲
    -0.18
    å¾Ĺèµ·
    -0.17
    é«ĺé¢ij
    -0.17
    atel
    -0.17
     Vict
    -0.17
    太å¤ļäºĨ
    -0.17
    handlers
    -0.17
    ITA
    -0.17
    itos
    -0.17
    POSITIVE LOGITS
    çªģçł´åı£
    0.32
    çļĦä¸Ģéĥ¨åĪĨ
    0.27
    人æ°ijæľįåĬ¡
    0.24
    çļĦä¸Ģåijĺ
    0.23
    parate
    0.23
    åĪ©åĻ¨
    0.23
     follows
    0.22
    æīĭ段
    0.22
    gard
    0.22
     váºŃy
    0.22
    Activations Density 0.351%

    No Known Activations