© 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. 39818
    Prev
    Next
    INDEX
    Explanations

    code structure and identifiers

    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
    emaan
    -0.08
     Mort
    -0.07
     Miser
    -0.07
    åĮ»çĶŁè¯´
    -0.07
    auce
    -0.07
    eed
    -0.07
    oons
    -0.06
    à¤Ĥत
    -0.06
    etos
    -0.06
    åĥļ
    -0.06
    POSITIVE LOGITS
     indict
    0.08
    æľķ
    0.07
    çķª
    0.07
    liwe
    0.07
    riad
    0.07
     rê
    0.07
     Mattis
    0.07
     Buf
    0.07
    toral
    0.07
    रà¥įफ
    0.07
    Activations Density 0.001%

    No Known Activations