© 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. 15357
    Prev
    Next
    INDEX
    Explanations

    before events or statements

    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
    åķ¬
    -0.20
    _repository
    -0.19
    ERING
    -0.19
    tá
    -0.18
    ableView
    -0.18
    ernote
    -0.18
    reten
    -0.18
    urette
    -0.17
    æĹ¥åIJİ
    -0.17
    ä¸Ģ大æĹ©
    -0.17
    POSITIVE LOGITS
    /out
    0.19
    -fashioned
    0.19
     occasions
    0.18
    å°±åºĶ该
    0.18
    ç¼Ģ
    0.17
    de
    0.17
    ici
    0.17
    говоÑĢ
    0.17
     Äijây
    0.17
    ork
    0.16
    Activations Density 0.017%

    No Known Activations