© 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. 38167
    Prev
    Next
    INDEX
    Explanations

    HTML tags and attributes

    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
    ä¸į缸
    -0.07
    ekar
    -0.07
    ä¹ĭ交
    -0.07
    edur
    -0.07
    _RUNTIME
    -0.07
    akh
    -0.07
     indexed
    -0.06
    ient
    -0.06
    æ½ĩæ¹ĺ
    -0.06
     panels
    -0.06
    POSITIVE LOGITS
    /title
    0.08
     text
    0.08
    _inside
    0.08
    æĸĩåŃĹ
    0.08
    åľ¨éĩĮéĿ¢
    0.07
     fluent
    0.07
    /native
    0.07
    æķijåij½
    0.07
    .createTextNode
    0.07
    毫åħĭ
    0.07
    Activations Density 0.123%

    No Known Activations