© 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. 13305
    Prev
    Next
    INDEX
    Explanations

    /licenses or MIT license

    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
    ultipart
    -0.21
    积累
    -0.19
    æ¯Ĵç´ł
    -0.18
    eing
    -0.17
    oined
    -0.17
    éŀŃ
    -0.17
    lington
    -0.17
     опÑĭ
    -0.17
    vard
    -0.17
    loth
    -0.17
    POSITIVE LOGITS
    åĦ¿
    0.19
    çħĮ
    0.19
    ellen
    0.19
    åĿİ
    0.19
     gest
    0.18
    å²ļ
    0.18
    DIRECT
    0.18
     Indust
    0.18
     DN
    0.18
    OrNull
    0.18
    Activations Density 0.001%

    No Known Activations