© 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. 14150
    Prev
    Next
    INDEX
    Explanations

    furnished or furnishings

    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
    -0.17
    ilver
    -0.17
    ëĭĪëĭ¤
    -0.16
    ൻ
    -0.16
    áŀł
    -0.16
    sters
    -0.16
    gos
    -0.15
    gie
    -0.15
    ccount
    -0.15
    zel
    -0.15
    POSITIVE LOGITS
    MENTS
    0.20
    ment
    0.20
    ings
    0.20
    ments
    0.20
    äºĨä¸Ģ个
    0.20
    ãģĹãģ¾ãģĨ
    0.20
    anted
    0.17
    ä¸įäºĨ
    0.17
    edImage
    0.16
    ale
    0.16
    Activations Density 0.006%

    No Known Activations