© 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. 28312
    Prev
    Next
    INDEX
    Explanations

    helper class or object

    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
    ////////////////////////////////////////////////////////////////////////////
    -0.06
    /or
    -0.06
    两åѦä¸Ģåģļ
    -0.06
    ï¸ı
    -0.06
     '
    -0.06
    åħ¶
    -0.05
    ä¹ĭäºİ
    -0.05
    ↵
    -0.05
    awk
    -0.05
    POSITIVE LOGITS
    èĩªå·±
    0.18
    èĩªå·±æ²¡æľī
    0.14
    èĩªå·±èº«ä¸Ĭ
    0.12
    èĩªå·±è¢«
    0.12
    èĩªå·±éĥ½
    0.12
    etheless
    0.11
    köd
    0.11
    notated
    0.10
    odore
    0.10
    enticator
    0.10
    Activations Density 0.691%

    No Known Activations