© 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. 4346
    Prev
    Next
    INDEX
    Explanations

    True after a question

    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
    -suite
    -0.10
    ahuan
    -0.08
    ppo
    -0.08
    suite
    -0.08
    ãģ®ãģĭãĤĤãģĹãĤĮ
    -0.08
    oland
    -0.07
    aken
    -0.07
    Å¡in
    -0.07
     ÑĢÑĥк
    -0.07
     lawy
    -0.07
    POSITIVE LOGITS
    åħ¬åı¸èĤ¡ç¥¨
    0.06
    尽管å¦ĤæѤ
    0.06
    avana
    0.06
    çĭĤ
    0.06
    á»ĥm
    0.06
    urgi
    0.06
    ersed
    0.06
    দি
    0.06
    è²ł
    0.06
    arnya
    0.06
    Activations Density 0.002%

    No Known Activations