© 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. 46356
    Prev
    Next
    INDEX
    Explanations

    picking from probabilities

    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
    åĪ»éª¨
    -0.08
    å§ĵ
    -0.08
    ËĩËĩ
    -0.08
    aget
    -0.08
    æ»ĭè¡¥
    -0.07
     berbel
    -0.07
    åIJ¹åĵį
    -0.07
    queta
    -0.07
    avs
    -0.07
    adet
    -0.07
    POSITIVE LOGITS
    illet
    0.07
    æĬĺ
    0.07
    溢åĩº
    0.06
    otte
    0.06
    zh
    0.06
    .same
    0.06
    çļĦ主
    0.06
    åºı
    0.06
    _rw
    0.06
    orum
    0.06
    Activations Density 0.015%

    No Known Activations