© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-14B
    5. 20-RESID-BATCHTOPK-65K__L0-80
    7. 12619
    Prev
    Next
    INDEX
    Explanations

    #include statements

    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
     prime
    -0.20
    -0.19
     of
    -0.19
     pro
    -0.19
    h
    -0.19
     s
    -0.19
    “
    -0.19
     indifferent
    -0.18
     their
    -0.18
    y
    -0.18
    POSITIVE LOGITS
    åľ¨çݩ家ä¸Ń
    0.22
    ä¿ĿèŃ·æĶ¿çŃĸ
    0.21
    çķ¶æĤ¨åľ¨
    0.21
    تÙĪج
    0.19
    æĸ°äººçݩ家
    0.19
    使çĶ¨ç¶²è·¯
    0.19
    æĻ°
    0.19
    INGS
    0.19
    該使çĶ¨èĢħ
    0.18
     Bearings
    0.18
    Activations Density 0.821%

    No Known Activations