© 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. 51523
    Prev
    Next
    INDEX
    Explanations

    row, row record, bold, ital

    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
    alias
    -0.07
    è¶ģ
    -0.06
    -has
    -0.06
    ce
    -0.06
    åį´ä¹Ł
    -0.06
    yh
    -0.06
    ander
    -0.06
    éĢīä¸Ģ
    -0.06
    ç½®ä¹ĭ
    -0.06
     ur
    -0.06
    POSITIVE LOGITS
     represents
    0.13
    代表
    0.11
    代表äºĨ
    0.11
     Represents
    0.10
     mewakili
    0.10
     representing
    0.10
    represent
    0.10
     representan
    0.09
     représente
    0.09
     represent
    0.09
    Activations Density 0.052%

    No Known Activations