© 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. 38735
    Prev
    Next
    INDEX
    Explanations

    Spanish

    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
    宿
    -0.07
     fare
    -0.07
    oport
    -0.06
    gh
    -0.06
    åħ´è¶£
    -0.06
    fare
    -0.06
    istro
    -0.06
    ystal
    -0.06
    atures
    -0.06
    æѦ
    -0.06
    POSITIVE LOGITS
    _TER
    0.08
    umbo
    0.08
    ãģ¨ãģ¯ãģĦãģĪ
    0.08
    è°ģéĥ½
    0.07
    etje
    0.07
    JET
    0.07
    ubu
    0.07
     Ano
    0.07
     PROGMEM
    0.07
    orso
    0.07
    Activations Density 0.219%

    No Known Activations