© 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. 61606
    Prev
    Next
    INDEX
    Explanations

    methods to analyze or validate

    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
    åľ¨åĪ«äºº
    -0.08
    çľ¾
    -0.07
     Individual
    -0.07
    ä»ĺåĩºçļĦ
    -0.07
    çĸ²åĬ³
    -0.07
    hubungan
    -0.07
    _OUTPUT
    -0.07
    obel
    -0.06
    onais
    -0.06
    åĪ°å¤§
    -0.06
    POSITIVE LOGITS
    åħ¬æīĢ
    0.08
    нÑij
    0.07
    _HOOK
    0.07
     Germ
    0.07
    åĭ¾
    0.07
    anya
    0.07
    ленÑĮ
    0.07
    /cache
    0.07
    ean
    0.07
    anel
    0.07
    Activations Density 0.001%

    No Known Activations