© 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. 14538
    Prev
    Next
    INDEX
    Explanations

    search results for

    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
    OUN
    -0.19
    ast
    -0.19
     Nad
    -0.18
     seam
    -0.18
    ç°¸
    -0.18
    LY
    -0.18
    符
    -0.18
     Derrick
    -0.18
     Barn
    -0.17
    olg
    -0.17
    POSITIVE LOGITS
    èĤļ
    0.19
    个å¤ļ
    0.19
    梳
    0.19
    ariat
    0.19
    udi
    0.18
    ÑĢажа
    0.18
    çªŁ
    0.18
    åı«å£°
    0.18
    买家
    0.18
    æªİ
    0.18
    Activations Density 0.010%

    No Known Activations