© 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. 37840
    Prev
    Next
    INDEX
    Explanations

    if followed by a new topic

    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
    å¿ĥæĤ¦
    -0.07
    entially
    -0.06
    ä¸ĢèĦļ
    -0.06
    embe
    -0.06
    伪
    -0.06
    读书ç¬Ķè®°
    -0.06
    ÙĦÙĬÙĦ
    -0.06
    æľī空
    -0.06
    DataSource
    -0.06
    人影
    -0.06
    POSITIVE LOGITS
    abria
    0.08
    tourn
    0.08
    вод
    0.08
    над
    0.07
    åħ¨ç¾İ
    0.07
    常常ä¼ļ
    0.07
    adow
    0.07
    .raise
    0.07
     recomm
    0.07
    _tw
    0.07
    Activations Density 0.001%

    No Known Activations