© 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. 34176
    Prev
    Next
    INDEX
    Explanations

    splitting into lists

    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
    æĻĵ举
    -0.06
    gid
    -0.06
     gid
    -0.06
    大åĨĻ
    -0.06
    pkg
    -0.06
    acd
    -0.06
     Tua
    -0.06
    rund
    -0.06
     Alic
    -0.06
    pin
    -0.06
    POSITIVE LOGITS
     categorized
    0.11
    ategorized
    0.11
     categor
    0.11
    ategor
    0.10
     Categor
    0.09
     categorie
    0.09
     separado
    0.09
    åĪĨãģij
    0.09
     segregated
    0.09
    åĪĨç»Ħ
    0.09
    Activations Density 0.142%

    No Known Activations