© 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. 22568
    Prev
    Next
    INDEX
    Explanations

    lengths and counts

    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
    çIJĨ
    -0.06
    \system
    -0.06
    äºķ
    -0.06
    ç§Ģæīį
    -0.06
     Cow
    -0.06
     cow
    -0.06
    çijŁ
    -0.06
    новÑĮ
    -0.06
     carn
    -0.06
     Maid
    -0.06
    POSITIVE LOGITS
    åĩºåIJį
    0.08
     memp
    0.07
    çŁ¥åħ¶
    0.07
    árt
    0.07
    ugu
    0.07
    ontro
    0.07
    uelas
    0.07
     handsome
    0.07
    CLU
    0.07
     menggel
    0.07
    Activations Density 0.012%

    No Known Activations