© 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. 14778
    Prev
    Next
    INDEX
    Explanations

    sitting on or down

    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
    hand
    -0.21
    ëį°
    -0.18
    -0.16
    åİ©
    -0.16
     erection
    -0.15
    hire
    -0.15
    mium
    -0.15
    zent
    -0.15
    éĿ¢è²Į
    -0.14
    éģĴ
    -0.14
    POSITIVE LOGITS
    uate
    0.24
    uations
    0.21
    ings
    0.20
    uation
    0.19
    ä¸ĭæĿ¥
    0.19
    -up
    0.19
    erville
    0.18
    uated
    0.18
    zelf
    0.18
    irical
    0.18
    Activations Density 0.031%

    No Known Activations