© 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. 55989
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions or text snippets

    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
     przej
    -0.07
    courses
    -0.07
    åĵ²
    -0.07
    yra
    -0.07
     courses
    -0.07
    æľªç»ı许åı¯
    -0.06
    agni
    -0.06
    imt
    -0.06
    èĢĮåħ¶ä»ĸ
    -0.06
    ä¸įèĭŁ
    -0.06
    POSITIVE LOGITS
    noop
    0.07
    éŁ
    0.07
    ÅĤow
    0.07
    ryw
    0.07
    ä¸ĩéĩĮ
    0.07
    aliz
    0.07
    leks
    0.07
    éĢģèµ°
    0.07
    ardan
    0.07
    çİ¥
    0.07
    Activations Density 0.007%

    No Known Activations