© 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. 16341
    Prev
    Next
    INDEX
    Explanations

    Cert, Stamp, bet, Font, Script, Golf, code, block

    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
    HU
    -0.18
    valuator
    -0.17
    ipment
    -0.17
    anners
    -0.17
    Javascript
    -0.17
    jac
    -0.17
    há»ķ
    -0.16
    CHANT
    -0.16
    utes
    -0.16
     Javascript
    -0.16
    POSITIVE LOGITS
    ä¹ĭ家
    0.24
    pedia
    0.22
    头æĿ¡
    0.21
    ä¹ĭæĺŁ
    0.20
    çĨĬçĮ«
    0.20
    ä¸ĸ纪
    0.20
    交æĺĵæīĢ
    0.20
    Union
    0.19
    atica
    0.19
    åĨįéĢł
    0.19
    Activations Density 0.271%

    No Known Activations