© 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. 2584
    Prev
    Next
    INDEX
    Explanations

    Release or Debug configuration

    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
    cape
    -0.07
    osoph
    -0.06
    åĽŀ家
    -0.06
    ä¸Ģ
    -0.06
    ored
    -0.06
    borough
    -0.06
    olog
    -0.06
    ovic
    -0.06
    çĩ
    -0.06
    aled
    -0.06
    POSITIVE LOGITS
    izzi
    0.08
    plx
    0.07
    imately
    0.07
    yä
    0.07
    ewel
    0.07
    ELTS
    0.07
    ÃŃmp
    0.07
    áĢ¸
    0.07
    踩è¿ĩ
    0.07
    覽
    0.07
    Activations Density 0.009%

    No Known Activations