© 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. 13664
    Prev
    Next
    INDEX
    Explanations

    punctuation and symbols in code/structured text

    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
    ingleton
    -0.20
    æ°¸åĪ©
    -0.18
    å¹´ä¸ŃåĽ½
    -0.18
    èĢĮåľ¨
    -0.18
    å¹³åĿĩæ¯ı
    -0.18
    eor
    -0.18
    ameda
    -0.17
     EXPRESS
    -0.17
    DOT
    -0.17
    avic
    -0.17
    POSITIVE LOGITS
    :
    0.23
    +:
    0.21
    ():
    0.21
    å¾Īéĩįè¦ģ
    0.21
    $:
    0.21
     {}:
    0.20
    "":
    0.19
    ]:
    0.19
    auty
    0.19
     ):
    0.19
    Activations Density 0.202%

    No Known Activations