© 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. 2626
    Prev
    Next
    INDEX
    Explanations

    shapes or measurements ending in units

    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
    sius
    -0.09
    opedia
    -0.08
    vak
    -0.08
    åij»
    -0.08
    adini
    -0.08
    ownie
    -0.08
    ász
    -0.07
    STS
    -0.07
    ibel
    -0.07
    年建éĢł
    -0.07
    POSITIVE LOGITS
    å¾·å°Ķ
    0.07
    ed
    0.07
     tollen
    0.07
    haled
    0.06
    apon
    0.06
     containing
    0.06
    áĢ¸
    0.06
    ุ
    0.06
    åĪĺ家
    0.06
    ÑĩаÑĤ
    0.06
    Activations Density 0.002%

    No Known Activations