© 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. 16609
    Prev
    Next
    INDEX
    Explanations

    course of

    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
    оÑģÑĮ
    -0.20
    istic
    -0.19
    istration
    -0.18
    é¢ı
    -0.17
    tract
    -0.16
    tré
    -0.16
    ÑĤон
    -0.16
    archy
    -0.16
    thed
    -0.16
    å°¼äºļ
    -0.16
    POSITIVE LOGITS
    keeper
    0.23
    able
    0.22
    y
    0.18
    gres
    0.17
    ing
    0.17
    ARENT
    0.17
    -wide
    0.17
    åĵĩ
    0.17
    views
    0.16
    aqu
    0.16
    Activations Density 0.033%

    No Known Activations