© 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. 7451
    Prev
    Next
    INDEX
    Explanations

    if statements

    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
    anut
    -0.07
    μά
    -0.07
     tostring
    -0.07
    ruise
    -0.07
    vene
    -0.07
    ibur
    -0.06
    ãĥĬãĥ¼
    -0.06
     kris
    -0.06
    é«ĺçĤ¹
    -0.06
     cose
    -0.06
    POSITIVE LOGITS
    feu
    0.08
     Dickinson
    0.07
    åıĭçļĦ
    0.07
    åīįæľī
    0.07
    elat
    0.07
    ?}",
    0.06
    olik
    0.06
    ROID
    0.06
    argo
    0.06
    LK
    0.06
    Activations Density 0.044%

    No Known Activations