© 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. 32517
    Prev
    Next
    INDEX
    Explanations

    'th term

    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
    iland
    -0.08
    anh
    -0.07
    ÏĢÏĦ
    -0.07
    insky
    -0.06
    uit
    -0.06
    bios
    -0.06
    asti
    -0.06
    idable
    -0.06
    &apos
    -0.06
    ovsky
    -0.06
    POSITIVE LOGITS
    åĴĮ第
    0.10
    uple
    0.08
    sence
    0.08
    ttp
    0.07
    oday
    0.07
    ãģĹãģıãģ¯
    0.07
    ablish
    0.07
    ãģĨãģ¡ãģ«
    0.07
    nici
    0.07
     (_.
    0.07
    Activations Density 0.007%

    No Known Activations