© 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. 12728
    Prev
    Next
    INDEX
    Explanations

    punctuation and descriptive words

    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
     “
    -0.08
     “âĢ¦
    -0.08
    “
    -0.08
     “[
    -0.07
    ’
    -0.07
    ”
    -0.07
     âĢ¦
    -0.07
    ÙĩÙħØ©
    -0.06
    å°ijæľīçļĦ
    -0.06
    ’y
    -0.06
    POSITIVE LOGITS
     '
    0.09
     meticulously
    0.09
     esteemed
    0.09
     '(
    0.09
     captivating
    0.09
    è¿Ľè¡Įæ·±åħ¥
    0.09
    缸è¾ĥäºİ
    0.08
    (___
    0.08
    ...'
    0.08
    ิà¸į
    0.08
    Activations Density 0.005%

    No Known Activations