© 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. 13756
    Prev
    Next
    INDEX
    Explanations

    unique features, online videos, answer all

    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
     ampl
    -0.23
     SE
    -0.22
     arch
    -0.22
    .nom
    -0.21
     provoc
    -0.21
    iat
    -0.21
     Ban
    -0.20
     '
    -0.20
     A
    -0.20
     (
    -0.20
    POSITIVE LOGITS
     salopes
    0.31
    há»ķ
    0.29
     nuru
    0.28
    ãģĬäºĴ
    0.28
     tjejer
    0.28
     Erotische
    0.28
     modne
    0.27
     najb
    0.27
     Prostitutas
    0.27
     erotisk
    0.26
    Activations Density 0.057%

    No Known Activations