© 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. 12521
    Prev
    Next
    INDEX
    Explanations

    initialization functions for code

    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
    ç¬ŀ
    -0.20
    å±ķå¼Ģ
    -0.19
     tslint
    -0.18
    èĬ
    -0.18
    ACS
    -0.18
    инÑĭ
    -0.17
    à¸Ńà¸ģ
    -0.17
    toArray
    -0.17
    iban
    -0.17
    Õ»
    -0.17
    POSITIVE LOGITS
     огÑĢаниÑĩен
    0.19
    æ¯ıæĹ¥
    0.19
    åıŃ
    0.18
    ancellor
    0.18
    ä¸įåģļ
    0.17
    æĪijèĥ½
    0.17
    andest
    0.17
    âĹ»
    0.17
    åķĨåºĹ
    0.17
     Tiffany
    0.17
    Activations Density 0.931%

    No Known Activations