© 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. 46615
    Prev
    Next
    INDEX
    Explanations

    7+

    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
    лев
    -0.07
    æĢĸ
    -0.06
    zut
    -0.06
    ona
    -0.06
    quet
    -0.06
     Seg
    -0.06
    LING
    -0.06
    _URI
    -0.06
    éĢ¼
    -0.06
    okit
    -0.06
    POSITIVE LOGITS
    еÑĤка
    0.08
    ìĹŃìĿĦ
    0.08
    klan
    0.08
    ourn
    0.08
    åħ¬çĽĬæĢ§
    0.07
    ocas
    0.07
    该åħ¬åı¸çļĦ
    0.07
    ëħĢ
    0.07
    .Vertical
    0.07
    å½ĵåľ°äºº
    0.07
    Activations Density 0.001%

    No Known Activations