© 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. 11200
    Prev
    Next
    INDEX
    Explanations

    Mr. surname

    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
    羣æŃ£çļĦ
    -0.19
    ww
    -0.18
    åIJİéĿ¢çļĦ
    -0.18
    STYPE
    -0.18
    oÅĽci
    -0.17
    ITED
    -0.17
    ksi
    -0.17
    æĪijçļĦå¿ĥ
    -0.17
    ffee
    -0.17
    æĪij
    -0.17
    POSITIVE LOGITS
    omba
    0.20
    usat
    0.20
    髦
    0.18
    åĨĻéģĵ
    0.18
    åıĬ以ä¸Ĭ
    0.18
    æĶ¿æ³ķ
    0.17
    Speaker
    0.17
    鹬
    0.17
    æī§æķĻ
    0.17
    BEL
    0.17
    Activations Density 0.020%

    No Known Activations