© 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. 48011
    Prev
    Next
    INDEX
    Explanations

    question and answer pairings

    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
    /ubuntu
    -0.08
    acz
    -0.08
    Guess
    -0.08
    ä¸įèĭŁ
    -0.07
    eschi
    -0.07
    igente
    -0.07
    itarian
    -0.07
    ä¸įè´¥
    -0.07
    jun
    -0.07
    ota
    -0.07
    POSITIVE LOGITS
    Originally
    0.12
    tl
    0.07
    toj
    0.07
    IRO
    0.07
    erton
    0.06
    ady
    0.06
     Cardoso
    0.06
     rop
    0.06
     getResources
    0.06
    lsa
    0.06
    Activations Density 0.062%

    No Known Activations