© 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. 29437
    Prev
    Next
    INDEX
    Explanations

    description or file details

    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
    er
    -0.10
    ting
    -0.10
    Ñĭ
    -0.08
    iness
    -0.08
    icket
    -0.07
    ****************************
    -0.07
    icism
    -0.07
    zinho
    -0.07
    ×Ļ
    -0.07
    eru
    -0.07
    POSITIVE LOGITS
    ormais
    0.13
    jenigen
    0.12
    ness
    0.11
    onical
    0.10
     milliers
    0.10
    cente
    0.10
    cript
    0.10
     centaines
    0.10
    nya
    0.09
    centes
    0.09
    Activations Density 0.048%

    No Known Activations