© 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. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 55763
    Prev
    Next
    INDEX
    Explanations

    Here is

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    rels
    -0.07
    -modules
    -0.07
     à¸ķุล
    -0.06
    amarca
    -0.06
    æµĭ
    -0.06
    çijŁ
    -0.06
    unger
    -0.06
    eler
    -0.06
    è°ģçŁ¥
    -0.06
    å
    -0.06
    POSITIVE LOGITS
    ulich
    0.08
    azu
    0.08
    pered
    0.07
     Merke
    0.07
    æłĹåŃIJ
    0.07
    æĬķ
    0.07
    ÑģÑĭл
    0.07
     mı
    0.07
    odka
    0.06
    ló
    0.06
    Activations Density 0.001%

    No Known Activations