© 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. 32050
    Prev
    Next
    INDEX
    Explanations

    project management

    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
    æ±Ľ
    -0.07
    empre
    -0.07
    gether
    -0.07
    tedy
    -0.06
    enticate
    -0.06
    IpAddress
    -0.06
    (#)
    -0.06
    rael
    -0.06
    maal
    -0.06
    ãģķãģ¾
    -0.06
    POSITIVE LOGITS
    ophile
    0.08
    öl
    0.08
    -themed
    0.07
    öp
    0.07
    itters
    0.07
     versus
    0.06
    ä¸ĿçļĦ
    0.06
    åĽ½åħ¬
    0.06
    è£Ķ
    0.06
    äºĭä¸ļçļĦåıijå±ķ
    0.06
    Activations Density 1.498%

    No Known Activations