© 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. 8423
    Prev
    Next
    INDEX
    Explanations

    question/answer context

    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
    ersen
    -0.07
    itrine
    -0.07
    inti
    -0.07
    omma
    -0.07
    次äºİ
    -0.07
    ×ķף
    -0.07
    minat
    -0.07
    大å¢ŀ
    -0.07
    å¸ĤéĿ¢ä¸ĬçļĦ
    -0.07
    åı¤èĢģ
    -0.06
    POSITIVE LOGITS
    æ¯ıé¢ĺ
    0.10
    解é¢ĺ
    0.10
    解åĨ³éĹ®é¢ĺçļĦ
    0.09
    解åĨ³éĹ®é¢ĺ
    0.08
     calculations
    0.08
    解åĨ³
    0.08
     solving
    0.08
    _answer
    0.08
    åĽŀçŃĶéĹ®é¢ĺ
    0.08
     answer
    0.08
    Activations Density 0.023%

    No Known Activations