© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 9132
    Prev
    Next
    INDEX
    Explanations

    K+ and chemical formulas

    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
    äºĨä¸ĢåľĪ
    -0.08
    大åĪ©
    -0.08
    Ascii
    -0.07
    usst
    -0.07
    Inspectable
    -0.07
    odash
    -0.07
    onical
    -0.07
    áĥIJáĥļáĥĺ
    -0.07
    æ²Ļæ²Ļ
    -0.07
    <|repo_name|>
    -0.07
    POSITIVE LOGITS
    移åĬ¨çīĪ
    0.06
    饶
    0.06
    GRP
    0.06
    weigh
    0.06
    à¥ĩ
    0.06
    epsi
    0.06
    ä¸Ń庸
    0.06
     Port
    0.06
    æµĭ
    0.06
    mobile
    0.06
    Activations Density 0.006%

    No Known Activations