© 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. 20406
    Prev
    Next
    INDEX
    Explanations

    code following "for"

    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
    reon
    -0.07
    ếm
    -0.07
    uard
    -0.07
    ä¸Ģæĸĩ
    -0.07
    订
    -0.07
    ithe
    -0.07
    ãģ©ãĤĬ
    -0.06
    PID
    -0.06
    èķī
    -0.06
    åħĪåĪ°
    -0.06
    POSITIVE LOGITS
    efore
    0.07
    eree
    0.06
    æ²¹çĽIJ
    0.06
    CursorPosition
    0.06
    ieur
    0.06
    åħĥæ°Ķ
    0.06
    ãģªãĤĬ
    0.06
    åıĻ
    0.06
    ellan
    0.06
     scomp
    0.06
    Activations Density 0.008%

    No Known Activations