© 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. 2106
    Prev
    Next
    INDEX
    Explanations

    following clues

    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
    wner
    -0.09
    .defineProperty
    -0.08
    å¦Ĥå®ŀ
    -0.07
    contro
    -0.07
    athed
    -0.07
    -inv
    -0.07
    Ãły
    -0.07
    план
    -0.07
    subcategory
    -0.07
    å§ĶåĨħ
    -0.07
    POSITIVE LOGITS
     clues
    0.13
     clue
    0.10
    线索
    0.10
    çĮľæµĭ
    0.09
    æݨæĸŃ
    0.09
    迹象
    0.09
     likely
    0.09
    端åĢª
    0.09
     pistas
    0.08
    éĢıéľ²
    0.08
    Activations Density 0.030%

    No Known Activations