© 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. 61252
    Prev
    Next
    INDEX
    Explanations

    email message

    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
     handl
    -0.08
    rish
    -0.08
    秫
    -0.08
    otte
    -0.08
    )application
    -0.08
    urut
    -0.08
    æĸ°ç¤¾
    -0.08
    Thunk
    -0.08
    ordnet
    -0.08
    Òĵ
    -0.08
    POSITIVE LOGITS
    anas
    0.07
    a
    0.07
    æ²®
    0.06
    eral
    0.06
    è¤Ĵ
    0.06
    ç²Ĺ
    0.06
     trans
    0.05
    анда
    0.05
     PROP
    0.05
    DG
    0.05
    Activations Density 0.982%

    No Known Activations