© 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
    2. Qwen3-8B
    3. 18-RESID-BATCHTOPK-65K__L0-80
    4. 2049
    Prev
    Next
    INDEX
    Explanations

    Football player names

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-8b-saes/saes_Qwen_Qwen3-8B_batch_top_k/resid_post_layer_18
    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
    ä¸Ģä¸ĭåŃIJå°±
    -0.24
    istring
    -0.24
    æĥ´
    -0.23
    æ®ĭéħ·
    -0.23
    vertiser
    -0.23
    .ASCII
    -0.23
    _lit
    -0.23
     дело
    -0.23
    isoft
    -0.23
    æ¯ıèĤ¡
    -0.23
    POSITIVE LOGITS
     players
    0.27
     home
    0.26
    le
    0.25
     Jordan
    0.25
     Players
    0.25
     rall
    0.24
     playing
    0.24
     Muse
    0.23
     Real
    0.23
     muse
    0.23
    Activations Density 0.042%

    No Known Activations