© 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. 12140
    Prev
    Next
    INDEX
    Explanations

    merge

    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
    sel
    -0.17
     xuyên
    -0.16
    è´Łè´£åIJĮå¿Ĺ
    -0.16
     urge
    -0.15
    èĬ±å¼Ģ
    -0.15
    urge
    -0.15
    大åıij
    -0.15
    CLAIM
    -0.15
    辩è¯ģ
    -0.15
    gtest
    -0.15
    POSITIVE LOGITS
    åIJİçļĦ
    0.24
    Into
    0.20
    èĢĮæĪIJ
    0.19
    _into
    0.19
    into
    0.19
     Into
    0.18
    åĴª
    0.18
    é¬ĵ
    0.17
     into
    0.17
     Sons
    0.17
    Activations Density 0.023%

    No Known Activations