© 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. 16049
    Prev
    Next
    INDEX
    Explanations

    version identifiers and code structure

    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
    ä¸įåħĭ
    -0.25
    两级
    -0.20
    èĭŁ
    -0.20
    å¿«æį·
    -0.19
    èĩ¾
    -0.19
    ìĺµ
    -0.18
    æ¸ł
    -0.18
     predictable
    -0.18
    ÑĨе
    -0.18
     steal
    -0.17
    POSITIVE LOGITS
    å»Ĭ
    0.21
    amate
    0.21
    å¤§åĽ½
    0.20
    THREAD
    0.19
    Assignable
    0.18
    ÑģÑĤÑĭ
    0.18
    imate
    0.18
    à°³
    0.18
    AtA
    0.18
     ÑĥкÑĢа
    0.18
    Activations Density 0.001%

    No Known Activations