© 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. 34019
    Prev
    Next
    INDEX
    Explanations

    carcinoma, oncogenesis, invader

    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
    ç¾Į
    -0.07
    APTER
    -0.07
    URLRequest
    -0.07
    åħ¼
    -0.07
    é¨
    -0.07
     Bakal
    -0.07
    artin
    -0.07
    å®Įçķ¢
    -0.07
    gge
    -0.07
    elsey
    -0.07
    POSITIVE LOGITS
    ç¨ĭ度
    0.07
     szemp
    0.07
     severity
    0.06
     subtly
    0.06
    ç¨ĭ度ä¸Ĭ
    0.06
    lable
    0.06
     subtle
    0.06
    åĪ©çĶ¨äºĨ
    0.06
    รà¹īาย
    0.06
    ocy
    0.06
    Activations Density 0.511%

    No Known Activations