© 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. 24471
    Prev
    Next
    INDEX
    Explanations

    options A, B, C, D, E, 6

    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
     Berm
    -0.08
    avers
    -0.08
    åĽ¾çŃī
    -0.07
    åŁł
    -0.07
     Liebl
    -0.07
     podendo
    -0.07
    ä»Ģä¹ĪéĹ®é¢ĺ
    -0.07
    è¿Ļæł·ä¸Ģ个
    -0.06
    ä»Ģä¹ĪåİŁåĽł
    -0.06
    æ°ı
    -0.06
    POSITIVE LOGITS
    chied
    0.07
    è¾ĥåݻ年
    0.07
    æľªåħį
    0.07
    ello
    0.07
    deka
    0.07
    ogramm
    0.07
    ukum
    0.06
    ugat
    0.06
    Ñĥк
    0.06
    ürk
    0.06
    Activations Density 0.001%

    No Known Activations