© 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. 61225
    Prev
    Next
    INDEX
    Explanations

    many-to-one relationships

    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
    ovich
    -0.07
    stringLiteral
    -0.07
    ÑĢÑĸн
    -0.07
    家åĸ»æĪ·æĻĵ
    -0.07
    elui
    -0.07
    صاب
    -0.06
    ç·ıåIJĪ
    -0.06
    ysh
    -0.06
    ipas
    -0.06
    _bold
    -0.06
    POSITIVE LOGITS
    åħ³ç³»çļĦ
    0.12
    åħ³ç³»
    0.12
    åħ³ç³»ä¸Ń
    0.12
     relationships
    0.12
     relationship
    0.12
     relations
    0.11
    çļĦåħ³ç³»
    0.11
     Relationships
    0.11
    ê´Ģê³Ħ
    0.10
    .relationship
    0.10
    Activations Density 0.199%

    No Known Activations