© 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. 64245
    Prev
    Next
    INDEX
    Explanations

    numbers and variables like m, n, x, y

    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
    VID
    -0.08
    ired
    -0.08
    以太
    -0.07
    (Pos
    -0.07
    (?:
    -0.07
    ç´¯äºĨ
    -0.07
    AVE
    -0.07
    egah
    -0.07
    óa
    -0.06
    (...
    -0.06
    POSITIVE LOGITS
    ujan
    0.08
    mf
    0.07
    ullen
    0.07
     zero
    0.06
    å¥ĭè¿Ľ
    0.06
     nol
    0.06
    erland
    0.06
    çļĦåį±éĻ©
    0.06
    kez
    0.06
    leven
    0.06
    Activations Density 0.013%

    No Known Activations