© 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. 25951
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    our
    -0.10
    aver
    -0.07
    iz
    -0.07
    ud
    -0.07
    ru
    -0.07
     intuit
    -0.06
    comb
    -0.06
    act
    -0.06
    erb
    -0.06
    wall
    -0.06
    POSITIVE LOGITS
    adelph
    0.08
    ookie
    0.08
     efters
    0.08
    tery
    0.08
    itava
    0.07
    azier
    0.07
    itale
    0.07
    åıĤ天
    0.07
    说å¾Ĺ
    0.07
    ecast
    0.07
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.