© 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. 20388
    Prev
    Next
    INDEX
    Explanations

    percent sign or percentage

    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
    px
    -0.08
    尽责
    -0.08
    .recycle
    -0.07
    åĨĬ
    -0.07
    -Smith
    -0.07
     ÑĢазÑĢе
    -0.07
    iro
    -0.07
    ä¸ŃéĻ¢
    -0.07
    nsk
    -0.07
    _SAN
    -0.07
    POSITIVE LOGITS
    çĻ¾åĪĨä¹ĭ
    0.13
     (%)
    0.11
     percentage
    0.10
    percentage
    0.10
     Percentage
    0.09
    çĻ¾åĪĨæ¯Ķ
    0.09
    percent
    0.09
    _percent
    0.09
     percent
    0.09
     percentages
    0.09
    Activations Density 0.078%

    No Known Activations