© 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. 7363
    Prev
    Next
    INDEX
    Explanations

    JSON code structure

    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
    EMAT
    -0.07
     scale
    -0.07
     Scale
    -0.07
    pn
    -0.07
    eil
    -0.07
    è¾ĥå¿«
    -0.06
     SCALE
    -0.06
    regen
    -0.06
     scop
    -0.06
    ihn
    -0.06
    POSITIVE LOGITS
    ENTA
    0.08
    è¿Ľä¸ĢæŃ¥
    0.08
    SA
    0.07
    çİīé¾Ļ
    0.07
     Dent
    0.07
    olland
    0.07
     dents
    0.07
    zeni
    0.07
    кла
    0.06
    è±ģ
    0.06
    Activations Density 0.353%

    No Known Activations