© 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. 49760
    Prev
    Next
    INDEX
    Explanations

    tech investor

    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
    ayne
    -0.08
    otar
    -0.07
     oct
    -0.07
    ÙĪÙĩ
    -0.07
    ukai
    -0.07
    ÙĪتÙĩ
    -0.07
    iqué
    -0.06
    ruÄį
    -0.06
    quine
    -0.06
    γκα
    -0.06
    POSITIVE LOGITS
    好康
    0.07
    翼翼
    0.07
     pha
    0.07
    涮
    0.07
     Confé
    0.07
    almaz
    0.07
    ÑĢоид
    0.07
    aios
    0.07
    hua
    0.07
    allocator
    0.07
    Activations Density 0.005%

    No Known Activations