© 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. 60557
    Prev
    Next
    INDEX
    Explanations

    numbers between 1 and 20

    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
    appa
    -0.07
    icit
    -0.06
    ại
    -0.06
    ances
    -0.06
     ch
    -0.06
    istar
    -0.06
    _arrow
    -0.06
    æĢ§åħ³èĬĤçĤİ
    -0.05
    jen
    -0.05
    ĩ
    -0.05
    POSITIVE LOGITS
    ORES
    0.09
    æĹ¥èµ·èĩ³
    0.09
    åħ¢åħ¢ä¸ļä¸ļ
    0.08
    leks
    0.08
    leine
    0.08
    æĪIJåĬŁåIJİåį³åı¯
    0.08
    ekre
    0.08
    heen
    0.08
    eless
    0.07
     пи
    0.07
    Activations Density 0.004%

    No Known Activations