© 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. 11917
    Prev
    Next
    INDEX
    Explanations

    Moses and Exodus

    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
    ness
    -0.20
    ship
    -0.19
    ingly
    -0.18
    ties
    -0.18
    apos
    -0.18
    ships
    -0.17
    ily
    -0.17
    çĸł
    -0.17
    tests
    -0.17
    nea
    -0.17
    POSITIVE LOGITS
    涯
    0.20
    inte
    0.18
    å¾Ģä¸ĭ
    0.17
    hid
    0.16
    hower
    0.16
    ppe
    0.16
    -era
    0.16
    ropa
    0.16
    anders
    0.16
    hma
    0.15
    Activations Density 0.003%

    No Known Activations