© 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. 13865
    Prev
    Next
    INDEX
    Explanations

    selection of items

    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
     Seymour
    -0.07
    å½»
    -0.07
    éĵ¶å±±
    -0.07
    è©£
    -0.06
    èĩ´è¿ľ
    -0.06
     Carta
    -0.06
    æĦıæĮĩ
    -0.06
    mas
    -0.06
    çłļ
    -0.06
    èĩ´
    -0.06
    POSITIVE LOGITS
     derfor
    0.08
    æīĢ以她
    0.08
    Scar
    0.07
    çľ¼çĿĽéĩĮ
    0.07
    -Token
    0.07
    åĪ°æѤ
    0.07
     dolg
    0.07
    å·«
    0.07
    allax
    0.07
    edor
    0.06
    Activations Density 0.563%

    No Known Activations