© 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. 2551
    Prev
    Next
    INDEX
    Explanations

    by, for, or about

    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
     Istitu
    -0.11
    grafer
    -0.11
     **:**
    -0.11
     Pergun
    -0.11
     luder
    -0.11
    лÑĩа
    -0.10
     Prostitu
    -0.10
    issen
    -0.10
    понен
    -0.10
     weiber
    -0.10
    POSITIVE LOGITS
    Âł
    0.08
    0.07
    —
    0.06
    orts
    0.06
    t
    0.05
    ss
    0.05
    ↵
    0.05
    ä¸ĩ
    0.05
    IW
    0.05
    I
    0.05
    Activations Density 0.003%

    No Known Activations