© 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. 56257
    Prev
    Next
    INDEX
    Explanations

    academic paper section introductions

    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
    elsen
    -0.08
    azier
    -0.08
    losion
    -0.08
    馴
    -0.08
    .exclude
    -0.07
    uchs
    -0.07
    اج
    -0.07
    ocene
    -0.07
    ristol
    -0.07
    anski
    -0.07
    POSITIVE LOGITS
    å³
    0.08
    bil
    0.07
     Purs
    0.06
    äºijå³°
    0.06
     Bil
    0.06
    abcdefghijkl
    0.06
    ç¼Ģ
    0.06
    å·ŀ
    0.06
    涵
    0.06
    erty
    0.06
    Activations Density 0.018%

    No Known Activations