© 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. 32576
    Prev
    Next
    INDEX
    Explanations

    index after punctuation

    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
    çĽ¸ä¼¼æĸĩçĮ®
    -0.07
    <|box_end|>
    -0.07
    arris
    -0.07
    enas
    -0.07
    /autoload
    -0.07
     singly
    -0.07
    ÑĪок
    -0.06
    ÑįÑĢ
    -0.06
    èĢĢ
    -0.06
    ensely
    -0.06
    POSITIVE LOGITS
    åħ·ä½ĵå¦Ĥä¸ĭ
    0.08
    jsc
    0.07
    æľīåħ³
    0.07
    æľīåħ³äºİ
    0.07
    AVA
    0.07
    ä¼ģä¸ļä¸Ń
    0.07
    OrCreate
    0.07
    vm
    0.07
    sav
    0.07
    ìł
    0.07
    Activations Density 0.041%

    No Known Activations