© 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. 8764
    Prev
    Next
    INDEX
    Explanations

    legal and factual situations

    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
    åı·åı¬
    -0.08
    eningen
    -0.08
    pras
    -0.07
    .require
    -0.07
    íĶĦëłĪ
    -0.07
    ationToken
    -0.07
    scribe
    -0.07
    æľ¬åĵģ
    -0.07
    erat
    -0.07
    è¿ĻäºĽä¸ľè¥¿
    -0.07
    POSITIVE LOGITS
    æ¶īåıĬåĪ°
    0.08
    æ¡Ī件ä¸Ń
    0.08
    æ¡Īæĥħ
    0.08
     situations
    0.08
    åľ¨å¤ĦçIJĨ
    0.07
    æ£ĺæīĭ
    0.07
    æ³ķå¾ĭéĹ®é¢ĺ
    0.07
    个æ¡Ī
    0.07
    æ¶īåıĬçļĦ
    0.07
    è¿Ļ个äºĭæĥħ
    0.07
    Activations Density 0.022%

    No Known Activations