© 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. 15333
    Prev
    Next
    INDEX
    Explanations

    measurements describing change

    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
    âīĤ
    -0.52
    㶲
    -0.51
    تÙĪج
    -0.42
    ãĥĵãĤ¸ãĥį
    -0.40
    _ComCallableWrapper
    -0.39
    ãĤ¢ãĥ¡ãĥª
    -0.39
    ãİĸ
    -0.39
    éĵ½
    -0.38
    ãģĬãģĻãģĻ
    -0.37
    ḧ
    -0.37
    POSITIVE LOGITS
    ðŁĺĽ
    0.32
    ðŁĺ¦
    0.30
    âĢ¦↵↵↵↵
    0.29
    âĻª↵↵
    0.28
    1
    0.27
     Fucked
    0.27
    q
    0.27
    2
    0.26
     Manus
    0.26
    âĢ½
    0.26
    Activations Density 15.631%

    No Known Activations