© 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. 9400
    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
    ä¸Ĭè¿°
    -0.07
    ä¸ĬéĿ¢çļĦ
    -0.07
    R
    -0.07
    M
    -0.06
    esso
    -0.06
    ÙĩÛĮ
    -0.06
    以ä¸ĬçļĦ
    -0.06
    *
    -0.06
    以ä¸Ĭ
    -0.06
    åĪļæīį
    -0.06
    POSITIVE LOGITS
    ½Ķ
    0.09
    stantiate
    0.08
    ä¸Ńè§Ħ
    0.08
    typings
    0.08
    à²Ł
    0.08
    OGRAPH
    0.08
    <Float
    0.08
    kunft
    0.08
    CHANT
    0.08
    Regs
    0.07
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.