© 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. 15167
    Prev
    Next
    INDEX
    Explanations

    shelving and platforms

    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
     exhaust
    -0.20
    linger
    -0.20
    ãĥIJãĥ¬
    -0.19
    é£Ĵ
    -0.19
    å¯ĨéĽĨ
    -0.18
    豪
    -0.18
    Mari
    -0.18
    é¬ĵ
    -0.17
    ecal
    -0.17
    sert
    -0.17
    POSITIVE LOGITS
    æ¡ĮéĿ¢
    0.24
    éĿ¢ç§¯çº¦
    0.23
    åİļ度
    0.22
    éĿ¢ç§¯
    0.21
     plate
    0.21
     slab
    0.21
    宽度
    0.20
    尺寸
    0.20
    åıįå¼¹
    0.20
    表éĿ¢
    0.20
    Activations Density 0.086%

    No Known Activations