© 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. 65029
    Prev
    Next
    INDEX
    Explanations

    eigenvalues, eigenvectors, transformation, group, ring

    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
    irma
    -0.07
     Einf
    -0.06
    aight
    -0.06
    çīĽç¾Ĭ
    -0.06
    asan
    -0.06
     Andr
    -0.06
     Batu
    -0.06
    forc
    -0.06
    orts
    -0.06
    IDENT
    -0.06
    POSITIVE LOGITS
    åij½åIJį为
    0.08
    ewis
    0.08
    uket
    0.07
    zü
    0.07
    olg
    0.07
    è®°
    0.07
    iete
    0.07
    è£ĺ
    0.07
    heim
    0.07
    设为
    0.07
    Activations Density 0.443%

    No Known Activations