© 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. 11602
    Prev
    Next
    INDEX
    Explanations

    list of demands

    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
    æĥĭ
    -0.23
    ä¸įå¿į
    -0.21
    éģįåıĬ
    -0.20
    丰å¯Į
    -0.20
    edin
    -0.20
    éĢĤæŶ
    -0.19
    ICO
    -0.19
    山路
    -0.18
     nearest
    -0.18
    tur
    -0.18
    POSITIVE LOGITS
    æĸ¹æ¡Ī
    0.30
    çļĦè¦ģæ±Ĥ
    0.27
    è¦ģæ±Ĥ
    0.27
     demands
    0.26
    egot
    0.23
    请æ±Ĥ
    0.23
     demanded
    0.22
     insisted
    0.22
     accept
    0.22
     acceptable
    0.22
    Activations Density 0.124%

    No Known Activations