© 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. 30275
    Prev
    Next
    INDEX
    Explanations

    file or card or cells

    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
    estad
    -0.09
    eny
    -0.08
    eness
    -0.08
    auc
    -0.08
    ailles
    -0.08
    áĬIJ
    -0.08
    ายà¸Ļ
    -0.08
    ron
    -0.07
    thood
    -0.07
    ems
    -0.07
    POSITIVE LOGITS
    ,
    0.06
    (s
    0.06
    ially
    0.06
    ccording
    0.06
    avel
    0.06
    uitar
    0.06
    δί
    0.06
    (es
    0.05
    ÏĢοίη
    0.05
    æĭ¶
    0.05
    Activations Density 0.280%

    No Known Activations