© 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. 40537
    Prev
    Next
    INDEX
    Explanations

    affinities, potential, values, internal, underlying

    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
    使çĶ¨åIJİ
    -0.07
    inkel
    -0.07
    WI
    -0.06
    éķ°
    -0.06
    à¹ĩà¸ļ
    -0.06
    æĪĸéĥ¨åĪĨ
    -0.06
    çİĭ大
    -0.06
    éĵ¸å°±
    -0.06
    nce
    -0.05
    _svc
    -0.05
    POSITIVE LOGITS
    lian
    0.08
    лип
    0.08
    æݧåĪ¶å¥½
    0.07
    å¤Ł
    0.07
    羣çļĦå¾Ī
    0.07
    #error
    0.07
    åĪ°åºķæĺ¯
    0.07
    ÑģÑģ
    0.07
    ιÏĥ
    0.07
    .relative
    0.07
    Activations Density 0.125%

    No Known Activations