© 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. 43047
    Prev
    Next
    INDEX
    Explanations

    code structure elements

    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
    馨
    -0.06
     Lage
    -0.06
    cing
    -0.06
    iva
    -0.06
    ellt
    -0.06
    antan
    -0.06
    å¼Ĥ
    -0.05
    නà·Ĭ
    -0.05
    çľĭåľ¨çľ¼éĩĮ
    -0.05
    Buffer
    -0.05
    POSITIVE LOGITS
    uÅŁ
    0.08
    arp
    0.08
    æľĢæĸ°æĽ´æĸ°
    0.08
    CHO
    0.08
    दान
    0.07
     Äijục
    0.07
    ertos
    0.07
    gnore
    0.07
    invitation
    0.07
    дини
    0.07
    Activations Density 0.002%

    No Known Activations