© 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. 16063
    Prev
    Next
    INDEX
    Explanations

    squared units or area

    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
     налиÑĩ
    -0.20
    ä¹ĭ乡
    -0.20
    çµĤãĤıãĤĬ
    -0.19
    çIJĨ工大åѦ
    -0.19
     Crus
    -0.18
    éķ¿çŁŃ
    -0.18
    maid
    -0.18
     length
    -0.18
    croll
    -0.18
    nonnull
    -0.18
    POSITIVE LOGITS
    éĿ¢ç§¯
    0.38
    éĿ¢ç§¯çº¦
    0.32
    æĢ»éĿ¢ç§¯
    0.30
     area
    0.28
    area
    0.28
    (area
    0.27
    .area
    0.26
    ä¸Ģçīĩ
    0.26
     AREA
    0.26
    /Area
    0.26
    Activations Density 0.066%

    No Known Activations