© 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. 12924
    Prev
    Next
    INDEX
    Explanations

    id assignment

    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
    eur
    -0.20
    mith
    -0.17
    ÑĤоÑĢ
    -0.17
    ev
    -0.16
    ez
    -0.15
    soever
    -0.15
    /ext
    -0.15
    ozy
    -0.15
    EVER
    -0.14
     Trident
    -0.14
    POSITIVE LOGITS
    ï¸ı
    0.21
    ENTITY
    0.20
    0.19
    ãģĦãĤĭ
    0.18
    ãģĦãĤĭãģ¨
    0.18
     pháºŃn
    0.18
    èle
    0.17
    entities
    0.17
    umen
    0.16
     quo
    0.16
    Activations Density 0.140%

    No Known Activations