© 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. 23511
    Prev
    Next
    INDEX
    Explanations

    misc, numbers

    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
    èĥ¡ä¹±
    -0.07
    opedia
    -0.07
    atten
    -0.07
    çĻ¾ç±³
    -0.07
    edb
    -0.07
    urie
    -0.06
    osz
    -0.06
    λογία
    -0.06
     Suomi
    -0.06
    wich
    -0.06
    POSITIVE LOGITS
    å©ķ
    0.08
     Misc
    0.07
     misc
    0.07
    _misc
    0.07
     aks
    0.06
    ì¡°
    0.06
    _MISC
    0.06
    hammer
    0.06
     seeded
    0.06
    ÑģÑĤÑĢе
    0.06
    Activations Density 0.026%

    No Known Activations