© 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. 16206
    Prev
    Next
    INDEX
    Explanations

    moderate heat

    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
    æ¶Įçİ°
    -0.23
    踢
    -0.21
    ãĥIJãĥ¼
    -0.21
    æ±Ģ
    -0.20
    åı«åģļ
    -0.19
    ä¾ĭå¤ĸ
    -0.19
    icorn
    -0.19
     Watts
    -0.19
    çĿ¦
    -0.19
    éĦĻ
    -0.19
    POSITIVE LOGITS
    ataka
    0.19
    éĴ±å¸ģ
    0.19
    çĬ¶æĢģä¸ĭ
    0.18
     Bellev
    0.17
    çĿĢéĩį
    0.17
    IVED
    0.17
    ront
    0.17
    ä¸ŃåĽ½ä¼łç»Ł
    0.17
     Nak
    0.17
    çĩĶ
    0.16
    Activations Density 0.002%

    No Known Activations