© 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. 22998
    Prev
    Next
    INDEX
    Explanations

    measurement units

    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
    èįŁ
    -0.08
    uji
    -0.07
    umo
    -0.07
    ulette
    -0.07
    .uf
    -0.06
    -INF
    -0.06
    å²Ľ
    -0.06
    רת
    -0.06
    @Service
    -0.06
    umas
    -0.06
    POSITIVE LOGITS
    å¿ĥäºĭ
    0.08
    /
    0.08
    resp
    0.07
    icke
    0.07
    驻马
    0.07
    atetime
    0.07
    itur
    0.07
    øre
    0.07
    folio
    0.06
    departure
    0.06
    Activations Density 0.044%

    No Known Activations