© 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. 57914
    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
    åıijå±ķä¸Ńå¿ĥ
    -0.09
    伯æģ©
    -0.08
    apus
    -0.08
    ضر
    -0.08
    马åı¯
    -0.07
    apol
    -0.07
    çªĹåīį
    -0.07
    idro
    -0.07
    åłĤçļĦ
    -0.07
    Russ
    -0.07
    POSITIVE LOGITS
    éĽĨ
    0.08
    ekk
    0.07
    tabil
    0.07
     attributable
    0.07
    ä¸įèĥľ
    0.07
    ä»°
    0.06
    ollen
    0.06
    secs
    0.06
    Insets
    0.06
    èĮĥ
    0.06
    Activations Density 0.000%

    No Known Activations