© 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. 15316
    Prev
    Next
    INDEX
    Explanations

    airfoil, chamber, field, foam, transfer

    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
    osz
    -0.09
    ÏįÏĦε
    -0.08
    åı¦å¤ĸè¿ĺæľī
    -0.08
    acher
    -0.08
    ÅŁe
    -0.08
    èĩªæĭĶ
    -0.08
    ukung
    -0.07
    amed
    -0.07
    Ñİд
    -0.07
     illet
    -0.07
    POSITIVE LOGITS
     corresponding
    0.07
    ä¹Łå°±æĺ¯
    0.06
     all
    0.05
    ultad
    0.05
    è£ı
    0.05
    çŃī主è¦ģ
    0.05
    haft
    0.05
    ellido
    0.05
    ationally
    0.05
    åħ³æľº
    0.05
    Activations Density 0.133%

    No Known Activations