© 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. 10950
    Prev
    Next
    INDEX
    Explanations

    ending with +

    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
    aylor
    -0.08
    ycin
    -0.08
    _DL
    -0.07
    cek
    -0.07
    estro
    -0.07
    angg
    -0.07
    ltre
    -0.07
    ewire
    -0.07
    جØŃ
    -0.07
    ichel
    -0.06
    POSITIVE LOGITS
    大家æĹı
    0.07
    ÂŃt
    0.07
    uze
    0.07
    pak
    0.06
    RID
    0.06
    ane
    0.06
    que
    0.06
    ographically
    0.06
    ãģ¶
    0.06
    ÂŃs
    0.06
    Activations Density 0.116%

    No Known Activations