© 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. 64672
    Prev
    Next
    INDEX
    Explanations

    principles

    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
    ross
    -0.09
    ãģĤãĤĮãģ°
    -0.08
    gest
    -0.08
    teni
    -0.07
    shine
    -0.07
    تاÙĨ
    -0.07
    تÙĬÙĨ
    -0.07
    Ñģ
    -0.07
    룬
    -0.07
    tp
    -0.07
    POSITIVE LOGITS
    ãģ©ãĤĤ
    0.09
    nable
    0.09
    iggio
    0.08
    Ø©
    0.08
     ê¹Ķ
    0.08
    uvre
    0.08
     vẹn
    0.08
    heit
    0.08
    áŁĭ
    0.08
    furter
    0.08
    Activations Density 0.001%

    No Known Activations