© 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. 15095
    Prev
    Next
    INDEX
    Explanations

    nanotechnology, nanometer, nanociencia

    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
    稿
    -0.20
    iveness
    -0.20
    unks
    -0.17
    ../../../
    -0.17
    aul
    -0.16
    oner
    -0.15
    ummer
    -0.15
    acher
    -0.15
    oire
    -0.15
    Ùħت
    -0.15
    POSITIVE LOGITS
    ê¹IJ
    0.21
    hood
    0.19
    о
    0.18
    bé
    0.18
    èĻ±
    0.18
    æİ¥è¿ĩ
    0.17
    izable
    0.17
    æ·±å¤Ħ
    0.17
    è¾Ī
    0.16
    èĬ¥
    0.16
    Activations Density 0.031%

    No Known Activations