© 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. 40722
    Prev
    Next
    INDEX
    Explanations

    I hear

    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
    åĨ²åĩ»
    -0.07
     tim
    -0.07
    Ñĸ
    -0.07
     entf
    -0.07
    anger
    -0.07
    avage
    -0.06
    端起
    -0.06
     PyErr
    -0.06
    roat
    -0.06
    itched
    -0.06
    POSITIVE LOGITS
    ç»Ī
    0.08
    ahnya
    0.07
     olsun
    0.07
    çĭŀ
    0.07
    oren
    0.07
    ìŀij
    0.07
     kone
    0.07
     Aks
    0.06
    ä¸Ģå¦Ĥ
    0.06
    tron
    0.06
    Activations Density 0.076%

    No Known Activations