© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 63101
    Prev
    Next
    INDEX
    Explanations

    percentages, numbers, or counts

    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
    çī¹æĸ°
    -0.07
    ica
    -0.07
     Eag
    -0.06
    arella
    -0.06
    _THRESH
    -0.06
    Ñįй
    -0.06
    æĸĩåĮĸä¼łæĴŃæľīéĻIJåħ¬åı¸
    -0.06
    ao
    -0.06
    aired
    -0.06
    ç§ijæĬĢåıijå±ķæľīéĻIJåħ¬åı¸
    -0.06
    POSITIVE LOGITS
    ãĢģ
    0.09
     maupun
    0.08
    atak
    0.08
    循
    0.07
    æĪĸ缺
    0.07
    óf
    0.07
     ãĢģ
    0.07
    ער
    0.07
    ÙĪاÙħ
    0.07
    æĪĸåĪłéĻ¤
    0.07
    Activations Density 0.022%

    No Known Activations