© 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. 11927
    Prev
    Next
    INDEX
    Explanations

    light-up, vibration, automatic, function, LED

    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
    åķĥ
    -0.22
    uiten
    -0.21
    okies
    -0.20
     Campbell
    -0.20
    uida
    -0.20
    è·¨è¶Ĭ
    -0.19
     Sunder
    -0.19
    .construct
    -0.19
    hek
    -0.19
    numerusform
    -0.19
    POSITIVE LOGITS
    å®ĥçļĦ
    0.27
    åĨħç½®
    0.25
    åĬŁèĥ½
    0.22
    çĽį
    0.21
     ÑĦÑĥнкÑĨи
    0.21
    Its
    0.20
     customizable
    0.20
    activated
    0.20
    ÑĮ
    0.20
    LED
    0.20
    Activations Density 0.081%

    No Known Activations