© 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. 21134
    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
    åīįè¿Ľ
    -0.07
    åĩł
    -0.07
     incid
    -0.07
    åĽłåħ¬
    -0.06
    eppe
    -0.06
    æ
    -0.06
    ijn
    -0.06
    åĽł
    -0.06
    ane
    -0.06
     backwards
    -0.06
    POSITIVE LOGITS
    yel
    0.07
    urrency
    0.07
    éron
    0.07
    ukaan
    0.07
    requ
    0.07
    髦
    0.07
    itrine
    0.07
    panies
    0.07
    ÏĦÏģο
    0.07
    -host
    0.07
    Activations Density 0.000%

    No Known Activations