© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 10897
    Prev
    Next
    INDEX
    Explanations

    code snippets parsing

    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
    åĬĽæīĢèĥ½åıĬ
    -0.07
    çĵľ
    -0.06
    åŃ¦å·¥
    -0.06
    StackSize
    -0.06
    सान
    -0.06
    èĬ¸
    -0.06
     Runnable
    -0.06
    peq
    -0.06
    false
    -0.06
    =__
    -0.06
    POSITIVE LOGITS
    @$
    0.08
    ubil
    0.08
    iverse
    0.07
    .wrap
    0.07
    ä¸į稳å®ļ
    0.07
     painstaking
    0.07
     Dernière
    0.07
    /raw
    0.07
    raw
    0.07
    lich
    0.07
    Activations Density 0.342%

    No Known Activations