© 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. 8437
    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
    acher
    -0.09
    è´°
    -0.07
    ÐĵС
    -0.07
    pires
    -0.07
    Powered
    -0.07
    代缴
    -0.07
    éļ
    -0.07
    haled
    -0.06
    ester
    -0.06
    ild
    -0.06
    POSITIVE LOGITS
    æĥ¯äºĨ
    0.08
    嫦
    0.07
    èĭ±æĸĩåIJįåŃĹ
    0.07
    à¸Ħล
    0.07
     Mode
    0.07
    å½·
    0.06
    èĢĮå°±
    0.06
    odox
    0.06
     männ
    0.06
     spä
    0.06
    Activations Density 0.000%

    No Known Activations