© 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. 46860
    Prev
    Next
    INDEX
    Explanations

    best followed by question or practice

    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
    ategorized
    -0.10
    zinho
    -0.10
    -esque
    -0.10
    erstellung
    -0.10
    áºŃt
    -0.10
    akwa
    -0.09
    alidad
    -0.09
    بطاÙĦ
    -0.09
    kenal
    -0.09
    stech
    -0.09
    POSITIVE LOGITS
    s
    0.12
    ablish
    0.11
    immung
    0.10
    -known
    0.09
    est
    0.09
    seller
    0.08
    owing
    0.08
    ened
    0.08
    imator
    0.08
    ening
    0.08
    Activations Density 0.049%

    No Known Activations