© 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. 46126
    Prev
    Next
    INDEX
    Explanations

    parts per million

    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
    raries
    -0.10
    imately
    -0.09
    denes
    -0.08
    åıĪæĪĸèĢħ
    -0.08
    abut
    -0.08
    ovil
    -0.08
    tori
    -0.08
    venes
    -0.08
    ocat
    -0.08
    jenigen
    -0.08
    POSITIVE LOGITS
    gnore
    0.07
    /pp
    0.07
    esus
    0.07
    гда
    0.07
    Ń
    0.07
    å·¦åı³çļĦ
    0.07
    /year
    0.07
    out
    0.07
    ìķ¼
    0.06
    i
    0.06
    Activations Density 0.012%

    No Known Activations