© 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. 16114
    Prev
    Next
    INDEX
    Explanations

    boot, redirects, kinetics

    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
    quet
    -0.21
    rant
    -0.19
    antro
    -0.19
    æŃĩ
    -0.18
    quoise
    -0.18
    hip
    -0.18
    keit
    -0.18
    croll
    -0.18
     CC
    -0.18
    对ä¸ŃåĽ½
    -0.18
    POSITIVE LOGITS
    ä»ķ
    0.22
    çİ»çĴĥ
    0.18
    ulk
    0.18
    pll
    0.18
    /GPL
    0.17
    -enabled
    0.17
     automáticamente
    0.16
    URI
    0.16
     forks
    0.16
    çĽijçĭ±
    0.16
    Activations Density 0.001%

    No Known Activations