© 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. 24360
    Prev
    Next
    INDEX
    Explanations

    representing indicating curves and relationships

    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
    ิà¸Ļ
    -0.08
    ogui
    -0.08
    èģĮ
    -0.07
    /renderer
    -0.07
    请ä¸İæĪij们èģĶç³»
    -0.07
    xCD
    -0.07
    -www
    -0.07
    aska
    -0.07
    临
    -0.07
    egos
    -0.07
    POSITIVE LOGITS
    代表äºĨ
    0.11
    代表
    0.11
    代表çĿĢ
    0.11
     representing
    0.10
    represent
    0.10
     indicating
    0.10
     représentant
    0.10
     signifies
    0.10
     indicates
    0.09
    表æĺİäºĨ
    0.09
    Activations Density 0.016%

    No Known Activations