© 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. 27831
    Prev
    Next
    INDEX
    Explanations

    fill in blanks

    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
    ütz
    -0.08
    è®®äºĭ
    -0.08
    eker
    -0.08
    çłį
    -0.07
    æİĤ
    -0.07
    packages
    -0.07
    éĻį
    -0.07
     impr
    -0.07
    _itr
    -0.07
    书åįķ
    -0.07
    POSITIVE LOGITS
    å¡«
    0.24
    填空
    0.23
     fill
    0.22
    å¡«åĨĻ
    0.22
    å¡«åħħ
    0.21
     filling
    0.21
    å¡«åħ¥
    0.21
     Fill
    0.21
    Fill
    0.20
    填空é¢ĺ
    0.19
    Activations Density 0.147%

    No Known Activations