© 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. 46722
    Prev
    Next
    INDEX
    Explanations

    political or governmental agenda

    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
    orti
    -0.10
    boro
    -0.09
    udir
    -0.09
    orrent
    -0.09
    ëĵł
    -0.08
    joj
    -0.08
    河山
    -0.08
    ẻ
    -0.08
    idth
    -0.08
    qed
    -0.08
    POSITIVE LOGITS
    以åıĬ对
    0.08
    .
    0.07
    ↵
    0.06
    家ä¼Ļ
    0.06
    ,
    0.06
    以åıĬåľ¨
    0.06
    ãģĹãĤĩ
    0.06
     *
    0.06
    0.06
    estro
    0.06
    Activations Density 0.004%

    No Known Activations