© 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. 39139
    Prev
    Next
    INDEX
    Explanations

    demodulator, decortication, dequeue, demyelination, component

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    weise
    -0.07
    ä¸įèµ·æĿ¥
    -0.07
    ggi
    -0.07
    à¸ĺรรม
    -0.06
    èµ·æĿ¥äºĨ
    -0.06
    ago
    -0.06
    æ·±è¿ľ
    -0.06
    دÙĬØ©
    -0.06
    ivi
    -0.06
     downfall
    -0.06
    POSITIVE LOGITS
     khá»ıi
    0.13
    adamente
    0.10
    /off
    0.09
    ÑĤÑĥÑĢи
    0.09
    äºĨçļĦ
    0.08
    /rem
    0.08
    /null
    0.08
    /remove
    0.08
    artment
    0.08
    URIComponent
    0.08
    Activations Density 0.098%

    No Known Activations