© 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. 55788
    Prev
    Next
    INDEX
    Explanations

    non-latin characters and symbols

    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
     "
    -0.07
    ent
    -0.07
    ant
    -0.06
    3
    -0.06
     –
    -0.06
    au
    -0.06
     —
    -0.06
    am
    -0.06
    ang
    -0.06
    :
    -0.06
    POSITIVE LOGITS
     à¸Ĺีà¹Īà¸Ķีà¸Ĺีà¹Īสุà¸Ķà¹ĥà¸Ļ
    0.10
    jala
    0.09
    俱ä¹IJéĥ¨
    0.09
    teres
    0.09
    isphere
    0.09
    %E
    0.09
    otify
    0.09
    ä¸Ģ亮
    0.08
    ”âĢ¦
    0.08
    ecker
    0.08
    Activations Density 0.098%

    No Known Activations