© 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. 29129
    Prev
    Next
    INDEX
    Explanations

    code: followed by identifier

    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
    .xhtml
    -0.07
    iedo
    -0.06
    agram
    -0.06
    å§Ķæīĺè¯ī讼代çIJĨ人
    -0.06
    ↵        ↵
    -0.06
    amba
    -0.06
    æĶ¯
    -0.06
    atro
    -0.06
     Pog
    -0.06
    amac
    -0.06
    POSITIVE LOGITS
    ogn
    0.08
    ÙĦس
    0.08
    ryn
    0.07
    ieri
    0.07
    razi
    0.07
    wiÄĻ
    0.07
    è¿ĩåħ³
    0.07
    ľad
    0.07
    åĵī
    0.07
     Dtype
    0.07
    Activations Density 0.058%

    No Known Activations