© 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. 56581
    Prev
    Next
    INDEX
    Explanations

    childhood

    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
    ia
    -0.08
    ä»Ģä¹Īäºĭ
    -0.07
    ensus
    -0.07
    çĽ£
    -0.07
    YA
    -0.06
    £
    -0.06
    িনি
    -0.06
    ãģįãģĮ
    -0.06
    Recv
    -0.06
    om
    -0.06
    POSITIVE LOGITS
    বাদ
    0.08
    iero
    0.08
    dex
    0.07
    thood
    0.07
    umph
    0.07
    Ïĥκ
    0.07
    å®ĹæŨ
    0.07
    ambo
    0.07
    ллÑı
    0.07
    æĹłéĹ´
    0.07
    Activations Density 0.013%

    No Known Activations