© 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. 17353
    Prev
    Next
    INDEX
    Explanations

    css position

    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
    ãģĤãģı
    -0.08
    oles
    -0.07
    //
    -0.07
     nød
    -0.07
    缸åħ³éĹ®çŃĶ
    -0.07
    enberg
    -0.07
     Premiership
    -0.07
    ÙĪاد
    -0.07
    <|box_end|>
    -0.07
    spiel
    -0.07
    POSITIVE LOGITS
    ijd
    0.07
    iju
    0.07
    inde
    0.06
    antaran
    0.06
    pera
    0.06
    łíļ
    0.06
    ngr
    0.06
    人家
    0.06
    INCT
    0.06
    dex
    0.06
    Activations Density 0.036%

    No Known Activations