© 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. 38609
    Prev
    Next
    INDEX
    Explanations

    CD4 T helper types

    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
    aszt
    -0.07
    æŃĩ
    -0.07
    uale
    -0.07
    大大çļĦ
    -0.07
    enha
    -0.07
    aisu
    -0.07
    anea
    -0.07
    zea
    -0.07
    halle
    -0.07
    км
    -0.07
    POSITIVE LOGITS
    medi
    0.07
    åŀĭ
    0.07
    å°±éĢģ
    0.07
    âĢij
    0.07
    çī¹åĪ«æĺ¯
    0.06
    åįłæĢ»
    0.06
    太éĥİ
    0.06
    obile
    0.06
    ritch
    0.06
    æĢ»éĩı
    0.06
    Activations Density 0.095%

    No Known Activations