© 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. 15650
    Prev
    Next
    INDEX
    Explanations

    incoming data type

    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
    aceous
    -0.20
    æł·çļĦ
    -0.19
     Ñģобой
    -0.19
    istic
    -0.18
    ifik
    -0.18
    åĪ©äºļ
    -0.17
    brook
    -0.16
    istical
    -0.16
    trib
    -0.15
    èŀŁ
    -0.15
    POSITIVE LOGITS
    /out
    0.34
    /up
    0.20
    /down
    0.20
    涯
    0.19
    es
    0.19
    -most
    0.19
    datable
    0.17
    stral
    0.17
    ä¹ĭåĬ¿
    0.17
    -looking
    0.17
    Activations Density 0.006%

    No Known Activations