© 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. 15669
    Prev
    Next
    INDEX
    Explanations

    et al

    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
    amental
    -0.24
    able
    -0.21
    less
    -0.19
    äºĮåŃĹ
    -0.18
    ful
    -0.17
    esimal
    -0.17
    aty
    -0.17
    ball
    -0.17
    oro
    -0.17
    ÐĽÐIJ
    -0.17
    POSITIVE LOGITS
    entifier
    0.19
    ç»ĦæĪIJçļĦ
    0.19
    ships
    0.18
    ðŁı¼
    0.17
    ðŁı»
    0.17
    /team
    0.17
    å¿ĥè¡Ģ
    0.17
    è¿Ŀç«ł
    0.17
    认为
    0.17
    /OR
    0.17
    Activations Density 0.037%

    No Known Activations