© 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. 13140
    Prev
    Next
    INDEX
    Explanations

    defensive coloring, surgeonfish, marine fish, poisonous

    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·ĺ
    -0.23
    åķľ
    -0.21
    Bone
    -0.20
    sink
    -0.20
     Bone
    -0.20
     Flo
    -0.20
    æĬ¿
    -0.20
    xFFFFFFFF
    -0.19
    çĬ´
    -0.19
    笼罩
    -0.19
    POSITIVE LOGITS
    éĺ²å¾¡
    0.24
    æľīæ¯Ĵ
    0.24
     Defensive
    0.21
     Coloring
    0.20
    èĬ±çº¹
    0.20
    éĴĪ
    0.20
    éĩĿ
    0.20
    åıįåĩ»
    0.20
    éĴĿ
    0.20
    éĩĬæĶ¾
    0.20
    Activations Density 0.060%

    No Known Activations