© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-14B
    5. 20-RESID-BATCHTOPK-65K__L0-80
    7. 11920
    Prev
    Next
    INDEX
    Explanations

    section identifiers and publication details

    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
    iable
    -0.20
    é¥ķ
    -0.17
    ortal
    -0.17
    éĥ½ä¸įæĺ¯
    -0.17
    igin
    -0.17
     Uzbek
    -0.17
    _MO
    -0.17
    å½ķ
    -0.17
    æķĻ导
    -0.17
    воÑĢ
    -0.17
    POSITIVE LOGITS
    æķ¢
    0.25
    èĢģåŃĹåı·
    0.20
     GiriÅŁ
    0.20
    å¦ĸ
    0.19
     Affero
    0.18
    зн
    0.18
    èĨı
    0.17
    asca
    0.17
    éŃĶçİĭ
    0.17
    /mock
    0.17
    Activations Density 0.017%

    No Known Activations