© 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. 11100
    Prev
    Next
    INDEX
    Explanations

    seabirds, IPython, Udacity, GDevelop, music

    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
    äºĨ大éĩıçļĦ
    -0.21
    é²Ķ
    -0.20
    è±ķ
    -0.20
    çĶ¨äºº
    -0.20
    é³Ŀ
    -0.19
    ongan
    -0.19
    culate
    -0.19
     mascara
    -0.19
    edImage
    -0.19
    èĤ±
    -0.19
    POSITIVE LOGITS
    å³»
    0.25
    伶
    0.20
    åı¹
    0.19
    æĹłæķĮ
    0.19
    éĻį
    0.18
    é¢Ĩ
    0.18
     vintage
    0.18
    nin
    0.18
    æī£
    0.17
    LinkId
    0.17
    Activations Density 0.003%

    No Known Activations