© 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. 48677
    Prev
    Next
    INDEX
    Explanations

    Now, I

    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
    bilang
    -0.07
    ï¸ı
    -0.07
    -0.07
    gnore
    -0.07
    ละ
    -0.07
    almaz
    -0.07
    /spec
    -0.07
    licable
    -0.07
    illions
    -0.07
     viol
    -0.06
    POSITIVE LOGITS
    assis
    0.09
    åĵªä¸Ģ个
    0.07
    inare
    0.07
    aris
    0.06
    uin
    0.06
    äºĮèĢħ
    0.06
    chas
    0.06
    in
    0.06
    _again
    0.06
    osz
    0.06
    Activations Density 0.090%

    No Known Activations