© 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. 10723
    Prev
    Next
    INDEX
    Explanations

    words with certain beginnings and endings

    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
     davran
    -0.18
     nasal
    -0.18
    åħħ足çļĦ
    -0.17
     Cha
    -0.17
     Redistributions
    -0.17
     Gonz
    -0.16
     Rag
    -0.16
    owie
    -0.16
    عر
    -0.16
     zer
    -0.16
    POSITIVE LOGITS
    unks
    0.21
    .simps
    0.20
    ses
    0.19
    åĻĹ
    0.18
    .sdk
    0.18
    ktop
    0.18
    oggle
    0.18
    ãģ¡ãģ¯
    0.18
    stance
    0.18
    ĺ
    0.18
    Activations Density 1.239%

    No Known Activations