© 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. 14492
    Prev
    Next
    INDEX
    Explanations

    Awards, titles, or specific roles

    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
    alker
    -0.08
    жай
    -0.07
    unker
    -0.07
     Modi
    -0.07
    anzo
    -0.07
    ä¸Ĭçģ«
    -0.07
    åħ»
    -0.07
    ä¸İæѤ
    -0.07
    abus
    -0.07
    ...',
    -0.07
    POSITIVE LOGITS
    ynie
    0.06
    erves
    0.06
    å¸ĪåħĦ
    0.06
     titul
    0.06
    inalg
    0.06
     Official
    0.06
     conting
    0.06
    åıĬ产åĵģ
    0.06
    è¯įæĿ¡
    0.06
    uff
    0.06
    Activations Density 0.051%

    No Known Activations