© 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. 14305
    Prev
    Next
    INDEX
    Explanations

    pink

    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
    çļ¿
    -0.18
    -même
    -0.17
    irement
    -0.15
    -cond
    -0.15
    ä¸Ģå®ļçļĦ
    -0.15
    Į
    -0.15
    unker
    -0.15
    regon
    -0.14
    icc
    -0.14
    rier
    -0.14
    POSITIVE LOGITS
    ish
    0.28
    ular
    0.25
    lets
    0.19
    ifying
    0.18
    -haired
    0.18
    ety
    0.18
    ï¸
    0.18
    -purple
    0.17
    side
    0.17
    erton
    0.17
    Activations Density 0.004%

    No Known Activations