© 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. 23605
    Prev
    Next
    INDEX
    Explanations

    code, syntax, file paths

    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
    .nodeType
    -0.07
     perk
    -0.07
    å¬
    -0.07
     latter
    -0.07
    ãi
    -0.07
    еÑģÑĤв
    -0.07
    orado
    -0.07
    æľĪä¾Ľ
    -0.06
    åĽ¾éĽĨ
    -0.06
    è»
    -0.06
    POSITIVE LOGITS
    ege
    0.08
    гаÑĤ
    0.07
    dden
    0.07
    opin
    0.07
    lesh
    0.06
    zzi
    0.06
    ejo
    0.06
    ê³łê°Ģ
    0.06
    æŃ¤é¡¹
    0.06
    ibs
    0.06
    Activations Density 0.013%

    No Known Activations