© 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. 12333
    Prev
    Next
    INDEX
    Explanations

    release dates

    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
    gil
    -0.20
    æķ´çIJĨ
    -0.19
    :///
    -0.19
    çī¹èī²äº§ä¸ļ
    -0.18
    åİĸ
    -0.18
    -da
    -0.17
    MER
    -0.17
    _mgmt
    -0.17
    egal
    -0.17
    AndGet
    -0.17
    POSITIVE LOGITS
    æ°ĺ
    0.21
    è¯ģåĪ¸æĬķèµĦ
    0.21
    è·º
    0.20
    åĤ¥
    0.20
    æݳ
    0.19
    cken
    0.19
    é¢Ħå®ļ
    0.19
    .appendTo
    0.18
    stm
    0.18
    pend
    0.18
    Activations Density 0.055%

    No Known Activations