© 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. 62296
    Prev
    Next
    INDEX
    Explanations

    LTS upgrades

    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
    åħ¶è¡Į为
    -0.07
    vey
    -0.06
    ibraltar
    -0.06
    izia
    -0.06
     recently
    -0.06
    ãĥĨãĥ¼
    -0.06
    uren
    -0.06
    åīįéĿ¢
    -0.06
    thon
    -0.06
    irim
    -0.06
    POSITIVE LOGITS
    essor
    0.09
    åıĺæĽ´ä¸º
    0.09
    ]->
    0.08
    åįĩåĪĿ
    0.08
    }->{
    0.08
    ldre
    0.08
    erto
    0.08
    ipas
    0.08
    å¾Ģ
    0.08
    ->_
    0.08
    Activations Density 0.006%

    No Known Activations