© 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. 33376
    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
    磨
    -0.07
    èIJ½èĬ±
    -0.07
    ä½ij
    -0.07
    åĬªåĬĽåģļåĪ°
    -0.07
    byss
    -0.07
    å¿ĺä¸įäºĨ
    -0.07
    hausen
    -0.06
    rief
    -0.06
    raft
    -0.06
    ẩu
    -0.06
    POSITIVE LOGITS
    ä¸įåľ¨
    0.08
    acia
    0.08
    secs
    0.07
    sek
    0.07
    agak
    0.07
    ignes
    0.07
    acias
    0.07
    iates
    0.07
    ìĦ¸ìĿĺ
    0.07
    Sec
    0.07
    Activations Density 0.000%

    No Known Activations