© 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. 46799
    Prev
    Next
    INDEX
    Explanations

    key value pair

    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
    èĩªå·±
    -0.07
    ä¹±
    -0.06
    enchmark
    -0.06
    èĩªå·±ä¹Ł
    -0.06
    erci
    -0.06
    geno
    -0.06
    éŃ
    -0.06
    balls
    -0.06
     Correa
    -0.06
    oczyn
    -0.06
    POSITIVE LOGITS
    Ø´ÛĮ
    0.09
    Ñijн
    0.08
    ç±»åŀĭ为
    0.08
    chten
    0.08
     berupa
    0.08
    ancier
    0.08
    -UA
    0.08
     Flake
    0.08
    stype
    0.08
     Fäl
    0.07
    Activations Density 0.009%

    No Known Activations