© 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. 16524
    Prev
    Next
    INDEX
    Explanations

    explicit formulas and expressions

    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
    æľīéģĵ
    -0.07
    åijĺçļĦ
    -0.07
    _NONE
    -0.07
    åħĪ端
    -0.07
    WD
    -0.06
    Ñļи
    -0.06
    eron
    -0.06
     оÑĦиÑĨиалÑĮнÑĭй
    -0.06
    iest
    -0.06
     Pej
    -0.06
    POSITIVE LOGITS
    åħ·ä½ĵçļĦãģ«
    0.08
    æݪ并举
    0.08
    OMP
    0.08
    andex
    0.08
     examples
    0.07
    ATAR
    0.07
    åħ·ä½ĵçļĦ
    0.07
    zza
    0.07
    dbuf
    0.07
     example
    0.07
    Activations Density 0.002%

    No Known Activations