© 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. 49531
    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
    ico
    -0.09
    ede
    -0.08
    ica
    -0.07
    icot
    -0.07
    ysi
    -0.07
    æŶäºĭ
    -0.07
    harmon
    -0.07
    pez
    -0.06
    alink
    -0.06
    istro
    -0.06
    POSITIVE LOGITS
    ORY
    0.07
    oja
    0.07
    éªĭ
    0.07
    æİĸ
    0.07
    oben
    0.06
    çŃĶå¤į
    0.06
    Qualifier
    0.06
    ldata
    0.06
    徨
    0.06
    æľĢä½³çŃĶæ¡Ī
    0.06
    Activations Density 0.000%

    No Known Activations