© 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. 15414
    Prev
    Next
    INDEX
    Explanations

    like comparison

    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
    raj
    -0.20
    .SE
    -0.19
    ä¹ĭ称
    -0.19
    aina
    -0.19
    cheon
    -0.19
    èĮ¬
    -0.19
    lator
    -0.19
    ught
    -0.19
    ä¸į论æĺ¯
    -0.18
    zik
    -0.18
    POSITIVE LOGITS
    -minded
    0.20
    åīįæīĢ
    0.19
    个å¤ļ
    0.18
     minded
    0.18
    -scale
    0.18
     straight
    0.17
    ä¸ĵéŨ
    0.17
     ìļ°
    0.17
    chan
    0.17
    è¿Īè¿Ľ
    0.17
    Activations Density 0.050%

    No Known Activations