© 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. 13415
    Prev
    Next
    INDEX
    Explanations

    number division or arithmetic

    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
    οÏħν
    -0.06
    ...,
    -0.06
    '(
    -0.06
    sid
    -0.06
    è·»
    -0.06
    gere
    -0.06
    .']
    -0.06
    unen
    -0.06
    ']/
    -0.06
    lots
    -0.06
    POSITIVE LOGITS
    licant
    0.08
    &view
    0.08
    igente
    0.08
    #get
    0.07
    Malloc
    0.07
     Hundred
    0.07
    çĮĸ
    0.07
    ensi
    0.07
    Å¡kod
    0.07
    bucks
    0.07
    Activations Density 0.020%

    No Known Activations