© 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. 64329
    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
    ness
    -0.10
    gether
    -0.10
    Ø©
    -0.10
    ities
    -0.10
    žil
    -0.09
    mehr
    -0.09
    adays
    -0.09
    ity
    -0.08
    ité
    -0.08
    yla
    -0.08
    POSITIVE LOGITS
    çļĦ
    0.07
    nya
    0.07
    ÛĮ
    0.07
    able
    0.07
    ëĬĺ
    0.07
    å®Įæ¯ķ
    0.07
    گاÙĩ
    0.07
    اتÙĩ
    0.06
    spflicht
    0.06
    Ùĩ
    0.06
    Activations Density 0.000%

    No Known Activations