© 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. 15045
    Prev
    Next
    INDEX
    Explanations

    numbers followed by a comma or specific names

    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
    åĦª
    -0.18
    arcy
    -0.18
    encrypted
    -0.18
     ذات
    -0.18
    wer
    -0.18
    磾
    -0.18
     recipro
    -0.17
    ä¸įå¿ĺ
    -0.17
    ä»ħ代表
    -0.17
    èĥĻ
    -0.17
    POSITIVE LOGITS
    .makedirs
    0.18
    ifix
    0.18
    ish
    0.18
    tsky
    0.18
    åīįåIJİ
    0.17
    éĴŀ
    0.17
    éĢĨåĬ¿
    0.17
    éŁŃèıľ
    0.17
    .ts
    0.17
    iano
    0.17
    Activations Density 0.117%

    No Known Activations