© 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. 8973
    Prev
    Next
    INDEX
    Explanations

    cleaning repeated symbols

    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
    è´Ń
    -0.08
    oczy
    -0.07
    ç¦ģ
    -0.07
    åĩĮä¹±
    -0.07
    åĬłåħ¥æĶ¶èĹı
    -0.07
    edal
    -0.07
    ife
    -0.07
    åĮĸ
    -0.06
    engl
    -0.06
    åĬ
    -0.06
    POSITIVE LOGITS
    saus
    0.08
     followed
    0.07
    _CLI
    0.07
    pell
    0.07
    @show
    0.07
    å¯ĨåĪĩæݥ触
    0.07
    大åĬĽå¼ĺæī¬
    0.07
    кÑĤо
    0.07
    lug
    0.07
    ADORES
    0.07
    Activations Density 0.015%

    No Known Activations