© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 15080
    Prev
    Next
    INDEX
    Explanations

    removing or exiting

    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
    /opt
    -0.08
    ilton
    -0.07
    漸
    -0.07
    æ¸IJè¿Ľ
    -0.07
    常温
    -0.07
    alm
    -0.07
    pat
    -0.07
    acor
    -0.07
    otti
    -0.06
    çļĦ主
    -0.06
    POSITIVE LOGITS
    çĦ¶åIJİåĨį
    0.16
    çĦ¶åIJİåıĪ
    0.14
     followed
    0.13
     puis
    0.13
     seguido
    0.12
    å¿ħé¡»åħĪ
    0.11
     briefly
    0.11
    çĦ¶åIJİ
    0.11
     temporarily
    0.11
     rá»ĵi
    0.11
    Activations Density 0.177%

    No Known Activations