© 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. 31293
    Prev
    Next
    INDEX
    Explanations

    fragments with layout or view

    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
    åĪĨä¹ĭ
    -0.08
    /photo
    -0.07
    /logo
    -0.07
    quilib
    -0.06
    èĩªå¾Ĺ
    -0.06
    èĬ³èįī
    -0.06
    rames
    -0.06
    <|box_end|>
    -0.06
    å®ī迪
    -0.06
    驾
    -0.06
    POSITIVE LOGITS
    -era
    0.07
    ÙĬÙĦات
    0.07
    âĦĸ
    0.07
     Prosp
    0.07
    ÑĥдаÑĢ
    0.07
    amic
    0.07
    zni
    0.07
    логи
    0.06
     Romana
    0.06
    ossal
    0.06
    Activations Density 0.106%

    No Known Activations