© 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. 48056
    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
    ned
    -0.07
    aged
    -0.07
    LOT
    -0.07
     catch
    -0.06
    纤
    -0.06
    _due
    -0.06
    imals
    -0.06
    åħĭåĬĽ
    -0.06
     catching
    -0.06
    aul
    -0.06
    POSITIVE LOGITS
    éĩįåĽŀ
    0.09
    à¦ĥ
    0.07
    çĤ¹åĩ»ä¸Ĭæĸ¹èĵĿåŃĹ
    0.07
    renom
    0.07
    -Identifier
    0.07
    é¦
    0.07
    eves
    0.07
    jure
    0.07
    -Key
    0.07
     Konferenz
    0.07
    Activations Density 0.000%

    No Known Activations