© 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. 12307
    Prev
    Next
    INDEX
    Explanations

    able to

    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
    æ¡ĥæĿİ
    -0.07
    NotAllowed
    -0.07
    FromString
    -0.07
    _beg
    -0.07
    ValueCollection
    -0.07
    integr
    -0.07
    åĪĽ
    -0.07
    antry
    -0.07
     gjerne
    -0.07
    MV
    -0.07
    POSITIVE LOGITS
    è¶³å¤ŁçļĦ
    0.13
    æľīè¶³å¤ŁçļĦ
    0.11
    å¤ŁçĶ¨
    0.11
     sufficient
    0.10
     enough
    0.10
     suficiente
    0.09
     adequate
    0.09
     adequately
    0.09
    ä¸įèĩ³äºİ
    0.08
    è¶³å¤Ł
    0.08
    Activations Density 0.039%

    No Known Activations