© 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. 13170
    Prev
    Next
    INDEX
    Explanations

    irrigation, Pegasus, Patch, cond, pump, register

    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
    涤
    -0.07
    andu
    -0.06
     Perkins
    -0.06
    ancis
    -0.06
    ITOR
    -0.06
    IZA
    -0.06
     необ
    -0.06
    æľº
    -0.06
    èį¼
    -0.06
    -0.06
    POSITIVE LOGITS
    olg
    0.08
    aday
    0.08
    urg
    0.08
    abler
    0.07
    prech
    0.07
    RIPT
    0.07
    æī¦
    0.07
    amani
    0.07
    @student
    0.07
    ä¸ĩå¥Ĺ
    0.07
    Activations Density 0.619%

    No Known Activations