© 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. 41475
    Prev
    Next
    INDEX
    Explanations

    investigation, deficiency

    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
    丽
    -0.08
    ιÏĥη
    -0.07
    åĩłæŃ¥
    -0.07
    .Validation
    -0.06
    -tool
    -0.06
    ilib
    -0.06
    ation
    -0.06
    atty
    -0.06
    éĥİ
    -0.06
    ources
    -0.06
    POSITIVE LOGITS
    svar
    0.08
    ANA
    0.08
    hlen
    0.07
    onos
    0.07
    女çļĦ
    0.07
    ahnya
    0.07
    UNT
    0.07
    Äija
    0.07
    ây
    0.07
    ayar
    0.07
    Activations Density 0.008%

    No Known Activations