© 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. 23655
    Prev
    Next
    INDEX
    Explanations

    following successor, aircraft, Kentucky

    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
    åĩ½æİĪ
    -0.08
    æĸĩåĵ²
    -0.08
    egar
    -0.08
    HandlerContext
    -0.08
    å½±å¸Ŀ
    -0.08
    á»ĩp
    -0.08
    åİ»çľĭ
    -0.08
    <|fim_suffix|>
    -0.07
    åĬłæĸ¯
    -0.07
    åħ¶éģĵ
    -0.07
    POSITIVE LOGITS
    å¦ĤåĽ¾æīĢ示
    0.06
    0.06
    ular
    0.06
    åıĪä½ķ
    0.06
    ual
    0.06
    L
    0.06
     ...
    0.06
    _translation
    0.06
    欲
    0.05
     translation
    0.05
    Activations Density 0.001%

    No Known Activations