© 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. 29045
    Prev
    Next
    INDEX
    Explanations

    enumeration or list items

    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
    æłijç«ĭ
    -0.06
    eil
    -0.06
     olev
    -0.06
    çĶ¨åĪ°
    -0.06
    ษ
    -0.06
    ثر
    -0.06
    noinspection
    -0.06
    æłijç«ĭäºĨ
    -0.05
    Å¡
    -0.05
    اÙĦات
    -0.05
    POSITIVE LOGITS
    itionally
    0.10
    egend
    0.08
    incontro
    0.08
    trut
    0.08
    ?p
    0.08
    æľĥè®ĵ
    0.08
    ckett
    0.07
    Ùģت
    0.07
    paro
    0.07
    0.07
    Activations Density 0.013%

    No Known Activations