© 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. 29051
    Prev
    Next
    INDEX
    Explanations

    political issues and decisions

    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
    æľī计åĪĴ
    -0.08
    esper
    -0.07
     ofApp
    -0.07
    æľīæĿ¡ä»¶çļĦ
    -0.07
    hme
    -0.07
    weg
    -0.07
    -strong
    -0.07
    aed
    -0.07
    aghan
    -0.06
    thur
    -0.06
    POSITIVE LOGITS
    éĹ®é¢ĺæŶ
    0.15
    éĹ®é¢ĺä¸Ĭ
    0.14
    æĸ¹éĿ¢çļĦéĹ®é¢ĺ
    0.13
    éĹ®é¢ĺ
    0.13
    çŃīéĹ®é¢ĺ
    0.12
     issue
    0.12
     issues
    0.12
    äºĭåħ³
    0.12
    åķıé¡Į
    0.11
    å®īåħ¨éĹ®é¢ĺ
    0.11
    Activations Density 0.203%

    No Known Activations