© 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. 42205
    Prev
    Next
    INDEX
    Explanations

    review keywords

    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
    ukul
    -0.08
    CUS
    -0.07
    Rest
    -0.07
    è´£ç¼ĸ
    -0.07
    yme
    -0.07
    trace
    -0.07
    ONO
    -0.07
    lopen
    -0.07
    uce
    -0.07
    heiten
    -0.07
    POSITIVE LOGITS
    ç²Ł
    0.07
    ÑĤнаÑı
    0.06
    缴åĪ°
    0.06
    olja
    0.06
    irken
    0.06
    swer
    0.06
     flick
    0.06
    onner
    0.06
    åĩĿ
    0.06
     propos
    0.06
    Activations Density 0.047%

    No Known Activations