© 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. 13051
    Prev
    Next
    INDEX
    Explanations

    square feet

    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
    _MED
    -0.21
    stick
    -0.19
    滥
    -0.19
    olesterol
    -0.18
     stump
    -0.18
     iNdEx
    -0.18
    _OCCURRED
    -0.18
    stub
    -0.18
    ulist
    -0.18
    sticks
    -0.17
    POSITIVE LOGITS
    建çŃijéĿ¢ç§¯
    0.30
    éĿ¢ç§¯çº¦
    0.29
    éĿ¢ç§¯
    0.28
    åİ¢
    0.25
    æĢ»éĿ¢ç§¯
    0.24
    åľºåľ°
    0.22
    ä½ĵéĩı
    0.22
    åĨħå¤ĸ
    0.22
    åĽ´
    0.22
    å¸ĥå±Ģ
    0.22
    Activations Density 0.011%

    No Known Activations