© 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. 33832
    Prev
    Next
    INDEX
    Explanations

    legal citation appendix number

    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
    psilon
    -0.07
    agni
    -0.07
    agn
    -0.07
    bbie
    -0.07
    æŀľçľŁ
    -0.06
    rio
    -0.06
    ning
    -0.06
    emer
    -0.06
    械
    -0.06
    ict
    -0.06
    POSITIVE LOGITS
    å½ĵä¹ĭ
    0.08
    大大å°ıå°ıçļĦ
    0.08
    andang
    0.08
    ead
    0.08
    anut
    0.08
    undos
    0.08
    SenderId
    0.07
    ientos
    0.07
    å·¦åı³çļĦ
    0.07
    tile
    0.07
    Activations Density 0.510%

    No Known Activations