© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 22941
    Prev
    Next
    INDEX
    Explanations

    replica symmetry breaking

    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
     magn
    -0.06
     flush
    -0.06
    askan
    -0.06
    à¹Ģห
    -0.06
    æķ¦
    -0.06
     chill
    -0.06
    çĿ«
    -0.06
     sper
    -0.06
     intens
    -0.06
    -0.06
    POSITIVE LOGITS
    解æķij
    0.09
    æŃ£éģĵ
    0.08
    allis
    0.08
    kov
    0.08
    elib
    0.08
    åħ¬ä»Ķ
    0.08
     Proceed
    0.08
    imately
    0.08
    å¤§åľ£
    0.08
    uzzi
    0.08
    Activations Density 0.004%

    No Known Activations