© 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. 28375
    Prev
    Next
    INDEX
    Explanations

    import statements

    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
    oron
    -0.08
    åĬ³åĬ¨èĥ½åĬĽ
    -0.07
    fone
    -0.07
    é¾Ħ
    -0.07
    sort
    -0.07
     lòng
    -0.06
    packed
    -0.06
    å¼Ģå¾Ĺ
    -0.06
    editable
    -0.06
    CELER
    -0.06
    POSITIVE LOGITS
    িনি
    0.07
    urah
    0.07
    imenti
    0.07
    _ASCII
    0.07
    AMI
    0.07
    mentos
    0.07
    engo
    0.06
    åij¦
    0.06
    WithDuration
    0.06
    ment
    0.06
    Activations Density 0.001%

    No Known Activations