© 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. 16281
    Prev
    Next
    INDEX
    Explanations

    saxophone or Saxon

    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
    æīĭæİĮ
    -0.17
    æĢĿ绪
    -0.16
    expanded
    -0.15
    ÑĥÑģÑĤ
    -0.15
    ศ
    -0.14
    害
    -0.14
    usc
    -0.14
    ÑĤÑĢо
    -0.14
    loon
    -0.14
    пÑĥÑģка
    -0.14
    POSITIVE LOGITS
    ophone
    0.23
    matic
    0.20
    liner
    0.19
    ãģĹãģ¾ãģĦ
    0.19
    auer
    0.19
    balls
    0.18
    åĪ©äºļ
    0.18
    ière
    0.18
    ically
    0.18
    etic
    0.18
    Activations Density 0.027%

    No Known Activations