© 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. 13516
    Prev
    Next
    INDEX
    Explanations

    up-to-date

    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
    ä¸ĬåįĪ
    -0.18
    hip
    -0.18
    ä¸ĭ鼨
    -0.16
    ystal
    -0.16
    REN
    -0.16
    ously
    -0.16
    ectomy
    -0.16
    hood
    -0.16
    iya
    -0.16
    apolis
    -0.15
    POSITIVE LOGITS
    /down
    0.32
    datable
    0.30
    dating
    0.25
    ðŁı»
    0.25
    dater
    0.24
    DATES
    0.24
    most
    0.23
    draft
    0.23
    sert
    0.22
    ðŁı¼
    0.21
    Activations Density 0.158%

    No Known Activations