© 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. 15216
    Prev
    Next
    INDEX
    Explanations

    .models Licenses

    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
    åı°å¤§
    -0.06
     mixing
    -0.06
    åħ¨æ°ij
    -0.06
    幡
    -0.06
    uwen
    -0.06
    âĢ
    -0.06
    åĿIJäºĨ
    -0.06
    æ··æIJŃ
    -0.06
     tart
    -0.06
    åĮłå¿ĥ
    -0.06
    POSITIVE LOGITS
    ipot
    0.08
    .handlers
    0.08
    AccessToken
    0.08
     representations
    0.08
     retrieve
    0.08
    ĵĺ
    0.08
    acic
    0.08
    LEG
    0.08
    Fetch
    0.08
     access
    0.08
    Activations Density 0.764%

    No Known Activations