© 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. 15389
    Prev
    Next
    INDEX
    Explanations

    first-aid supplies

    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
    PRS
    -0.18
    æıIJéĢŁ
    -0.17
    benh
    -0.17
    éĵ±
    -0.17
    éľĦ
    -0.17
    欲
    -0.17
    papers
    -0.17
    á»ijt
    -0.17
    åºķæ°Ķ
    -0.17
    pons
    -0.16
    POSITIVE LOGITS
    常è¯Ĩ
    0.27
    ç®±
    0.22
    å·¥ä½ľä¸Ń
    0.21
    çĶ¨åĵģ
    0.20
    sticks
    0.20
    æĢ¥æķij
    0.20
    çīĮ
    0.19
    åŁºæľ¬åİŁåĪĻ
    0.19
    needs
    0.19
    çī©åĵģ
    0.19
    Activations Density 0.003%

    No Known Activations