© 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. 12908
    Prev
    Next
    INDEX
    Explanations

    advice or consult

    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
     archetype
    -0.21
    å¼ĥ
    -0.21
    asc
    -0.19
    åį¿
    -0.19
     chù
    -0.19
    MUX
    -0.19
    å°ijè§ģ
    -0.19
    girls
    -0.19
    快讯
    -0.19
     puppies
    -0.18
    POSITIVE LOGITS
    ä¸ĵä¸ļ人士
    0.28
    ä¸ĵ家
    0.27
    å½ĵåľ°
    0.26
    å½ĵåľ°æĶ¿åºľ
    0.26
    èĢģå¸Ī
    0.25
    ä¸ĵä¸ļçļĦ
    0.25
    å½ĵåľ°çļĦ
    0.23
     expert
    0.23
    缸åħ³éĥ¨éŨ
    0.23
    主管
    0.21
    Activations Density 0.103%

    No Known Activations