© 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. 16206
    Prev
    Next
    INDEX
    Explanations

    small or smaller

    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
    大æĢĴ
    -0.11
    æīĭæľºç«Ļ
    -0.10
    ipel
    -0.10
    好åĩłæ¬¡
    -0.10
    ãĤ£
    -0.10
    erschaft
    -0.10
    vrier
    -0.10
    acimiento
    -0.10
    ahaya
    -0.10
    XObject
    -0.09
    POSITIVE LOGITS
    ness
    0.13
    ish
    0.12
    hood
    0.10
    -hearted
    0.09
    (er
    0.09
     جدÙĭا
    0.08
    ened
    0.08
    ,
    0.07
    ening
    0.07
    -scale
    0.07
    Activations Density 0.060%

    No Known Activations