© 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. 42414
    Prev
    Next
    INDEX
    Explanations

    we exhibit, show, identify

    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
    Ø©
    -0.15
    <|box_end|>
    -0.13
    ation
    -0.12
    ÙĬØ©
    -0.11
    ness
    -0.11
    èĩªå·±æ²¡æľī
    -0.10
    adays
    -0.10
    entication
    -0.09
    ÅĽmy
    -0.09
    witz
    -0.09
    POSITIVE LOGITS
    åĦ¿çļĦ
    0.09
    0.08
    ements
    0.07
     **
    0.07
    monic
    0.06
     "
    0.06
    ·
    0.06
    atively
    0.06
    <|box_start|>
    0.06
    ively
    0.06
    Activations Density 0.077%

    No Known Activations