© 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. 12158
    Prev
    Next
    INDEX
    Explanations

    bunch 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
    bol
    -0.19
    ãģ£ãģįãĤĬ
    -0.19
    imir
    -0.17
    coma
    -0.17
    aru
    -0.17
    çĶ¸
    -0.16
    äºĨä¸įå°ij
    -0.16
    tingham
    -0.16
    íİĻ
    -0.16
    ASI
    -0.16
    POSITIVE LOGITS
    s
    0.22
    ega
    0.18
    ed
    0.17
    es
    0.16
    rott
    0.16
    enas
    0.16
    eur
    0.16
    "
    0.16
    etwork
    0.16
    ogle
    0.16
    Activations Density 0.019%

    No Known Activations