© 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. 14681
    Prev
    Next
    INDEX
    Explanations

    start ... verbs

    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
    ility
    -0.19
    ç²¾åįİ
    -0.18
    amat
    -0.18
    adam
    -0.18
    زار
    -0.18
    èĭ±æīį
    -0.17
    hood
    -0.17
     till
    -0.17
    åĪ°äºĨ
    -0.17
    èĭ¥å¹²
    -0.17
    POSITIVE LOGITS
    cta
    0.24
    çĿĢæīĭ
    0.23
    ä¸ĢæŃ¥
    0.21
     dialogs
    0.20
    解åĨ³
    0.19
    lessly
    0.19
    cdr
    0.19
    ãģ¯ãģĺãĤģ
    0.18
    ç¼£
    0.18
    æŀĦ建
    0.18
    Activations Density 0.027%

    No Known Activations