© 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. 26189
    Prev
    Next
    INDEX
    Explanations

    critical value or threshold

    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
    δεί
    -0.07
    éŁ
    -0.07
    èĬĤ
    -0.07
    omy
    -0.07
    pace
    -0.07
    纸ä¸ļ
    -0.07
    å¦ĤæĦı
    -0.07
    éį¼
    -0.06
    åİŁäº§åľ°
    -0.06
     commod
    -0.06
    POSITIVE LOGITS
    estra
    0.08
    /latest
    0.07
    lest
    0.07
    æ§Ľ
    0.07
    akis
    0.07
    æŀģéĻIJ
    0.07
    åĴĮæľĢ
    0.07
    IMUM
    0.07
    临çķĮ
    0.07
    ãĤ¤ãĤ¯
    0.07
    Activations Density 0.007%

    No Known Activations