© 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. 12895
    Prev
    Next
    INDEX
    Explanations

    piece of

    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
    ship
    -0.26
    ships
    -0.23
    sWith
    -0.22
    çķĮçļĦ
    -0.18
    wich
    -0.18
    ìį¨
    -0.18
    sheet
    -0.18
    大家åĪĨ享
    -0.18
    shire
    -0.18
    漪
    -0.17
    POSITIVE LOGITS
    åĦ¿
    0.23
    åŃIJéĩĮ
    0.20
    urre
    0.17
    ure
    0.16
    etro
    0.16
    hips
    0.16
    ording
    0.16
    ORD
    0.16
    urement
    0.15
    åħĴ
    0.15
    Activations Density 0.022%

    No Known Activations