© 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. 42533
    Prev
    Next
    INDEX
    Explanations

    directions

    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
    watan
    -0.09
    ROTO
    -0.08
    thank
    -0.08
    trup
    -0.07
    iteDatabase
    -0.07
    tright
    -0.07
    ÑģмоÑĤÑĢиÑĤе
    -0.07
    affer
    -0.07
    thouse
    -0.07
    hle
    -0.07
    POSITIVE LOGITS
    ward
    0.11
    æĸ¹åIJijçļĦ
    0.09
     direction
    0.08
    æĸ¹åIJij
    0.08
    ous
    0.07
    æĸ¹ä½į
    0.07
    iros
    0.07
    ese
    0.07
    esian
    0.07
    -oriented
    0.07
    Activations Density 0.016%

    No Known Activations