© 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. 57101
    Prev
    Next
    INDEX
    Explanations

    vs

    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
    nce
    -0.06
    oci
    -0.06
    ize
    -0.06
    µ
    -0.06
    SZ
    -0.05
    â
    -0.05
    åį
    -0.05
     chill
    -0.05
    ç¨ĭ
    -0.05
    æĹłæīĢè°ĵ
    -0.05
    POSITIVE LOGITS
    Õ¡Õ½
    0.08
    æľ¨æĸ¯
    0.08
    ฯ
    0.08
    евÑģкого
    0.08
    ">//
    0.08
    èĤºèħij
    0.08
    ksam
    0.07
     ReturnType
    0.07
    PointerType
    0.07
    OfFile
    0.07
    Activations Density 0.012%

    No Known Activations