© 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. 63706
    Prev
    Next
    INDEX
    Explanations

    letters between curly braces

    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
    éħİ
    -0.08
    ä¸Ģä¾ĭ
    -0.07
    ä¹ĭä½ľ
    -0.06
    rophe
    -0.06
    inj
    -0.06
    åĢ¼å¾Ĺä¸ĢæıIJ
    -0.06
    åij¤
    -0.06
    ä¹ĭ乡
    -0.06
    rite
    -0.06
    æµĵæµĵ
    -0.06
    POSITIVE LOGITS
    ighth
    0.08
    ixa
    0.07
    (Util
    0.07
    å¸ķçī¹
    0.07
    engu
    0.07
    itters
    0.06
    jug
    0.06
    hta
    0.06
    åIJģ
    0.06
    νε
    0.06
    Activations Density 0.571%

    No Known Activations