© 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. 11076
    Prev
    Next
    INDEX
    Explanations

    make sense or make sure

    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
     ÐĶмиÑĤÑĢ
    -0.19
    entifier
    -0.19
     ÐIJлекÑģан
    -0.19
    ients
    -0.17
    móvel
    -0.17
    usk
    -0.17
    /out
    -0.17
    hoot
    -0.17
    ÑĢеги
    -0.16
    ync
    -0.16
    POSITIVE LOGITS
     sure
    0.32
    leine
    0.32
    äºĨä¸Ģ
    0.23
    äºĨä¸Ģåľº
    0.21
    个å°ı
    0.21
    äºĨä¸Ģ份
    0.20
    aways
    0.20
     sense
    0.20
    大äºĭ
    0.20
    åĩºæĿ¥çļĦ
    0.19
    Activations Density 0.113%

    No Known Activations