© 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. 12952
    Prev
    Next
    INDEX
    Explanations

    section of a road or length

    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
    åľ¨ä¸ĢæĹģ
    -0.21
    _corner
    -0.18
     ir
    -0.18
    éķ±
    -0.18
     comed
    -0.18
    goto
    -0.18
    opsy
    -0.18
     decipher
    -0.18
     vind
    -0.18
    -corner
    -0.18
    POSITIVE LOGITS
    段
    0.56
    è¿Ļ段
    0.46
    ä¸Ģ段
    0.46
    路段
    0.39
    éĤ£æ®µ
    0.38
     segment
    0.35
     Äijoạn
    0.32
    åľ°æ®µ
    0.31
    segment
    0.31
     segments
    0.30
    Activations Density 0.156%

    No Known Activations