© 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. 12037
    Prev
    Next
    INDEX
    Explanations

    program is free software

    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
    ä¸İåıijå±ķ
    -0.24
    åĴĮåıijå±ķ
    -0.21
    çĿ£å¯Ł
    -0.18
    stride
    -0.17
    èł¡
    -0.17
    æı©
    -0.17
    æ±²
    -0.17
    ष
    -0.17
    è¡·
    -0.17
     Chick
    -0.17
    POSITIVE LOGITS
    hood
    0.20
    ä¸Ģå°ģ
    0.20
    åĵŃ
    0.20
    /entity
    0.19
    abin
    0.18
    é²Ĥ
    0.18
    apphire
    0.17
    aptive
    0.17
    ancode
    0.17
    ships
    0.17
    Activations Density 0.066%

    No Known Activations