© 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. 40892
    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
    lå
    -0.08
    éĥİ
    -0.08
    éĹ·
    -0.08
    дÑĢе
    -0.08
    äºĮ代
    -0.08
    ='.
    -0.08
    agung
    -0.08
    .mx
    -0.07
    statt
    -0.07
    oyer
    -0.07
    POSITIVE LOGITS
    ue
    0.06
    çĭłçĭłåľ°
    0.06
     recons
    0.06
    ilet
    0.06
    usser
    0.06
    peg
    0.06
    çİ¥
    0.06
    lements
    0.06
    antic
    0.06
    alion
    0.06
    Activations Density 0.000%

    No Known Activations