© 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. 38148
    Prev
    Next
    INDEX
    Explanations

    citations and numbers

    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
    agin
    -0.07
    leist
    -0.07
    èī¯
    -0.07
    è¿ĺ
    -0.07
    knife
    -0.06
     rebuild
    -0.06
    ç»ĵ
    -0.06
    纨
    -0.06
    ä¸ĭæľŁ
    -0.06
    _shell
    -0.06
    POSITIVE LOGITS
     scre
    0.08
    _DECL
    0.08
    DRV
    0.07
    åĪ°è´¦
    0.07
    COVID
    0.07
    Drv
    0.07
    ulum
    0.07
    ORD
    0.06
    jom
    0.06
    æĪijçļĦå°ı
    0.06
    Activations Density 0.244%

    No Known Activations