© 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. 26214
    Prev
    Next
    INDEX
    Explanations

    writing for families

    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
     **
    -0.07
     *
    -0.07
     c
    -0.06
    -0.05
    ï¸ı
    -0.05
    C
    -0.05
    ä¸Ĭè¿°
    -0.05
    ,
    -0.05
     bang
    -0.05
    以ä¸Ĭ
    -0.05
    POSITIVE LOGITS
    زÛĮ
    0.09
    aiss
    0.09
    onga
    0.09
    'url
    0.09
    isy
    0.09
    &e
    0.08
    линд
    0.08
    laves
    0.08
    menti
    0.08
    &a
    0.08
    Activations Density 0.113%

    No Known Activations