© 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. 22102
    Prev
    Next
    INDEX
    Explanations

    numbers or digits

    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
    ront
    -0.08
    len
    -0.08
    oku
    -0.07
    .mit
    -0.07
    ascal
    -0.07
    ancar
    -0.07
    éħ¸çĶľèĭ¦è¾£
    -0.07
    ORK
    -0.07
    lene
    -0.07
    ATEG
    -0.07
    POSITIVE LOGITS
    å·¡
    0.07
    fim
    0.07
    plin
    0.07
     Barr
    0.06
     overs
    0.06
    uml
    0.06
    vel
    0.06
    æĬķ
    0.06
    ocache
    0.06
    _SYM
    0.06
    Activations Density 0.018%

    No Known Activations