© 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. 9030
    Prev
    Next
    INDEX
    Explanations

    provide background

    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
    å½¼
    -0.07
     .
    -0.06
    æĭ¿åĪ°
    -0.06
    Âł
    -0.06
    åıijæĮ¥å¥½
    -0.06
    -ish
    -0.06
    lair
    -0.06
    å°ijæľīçļĦ
    -0.06
    åľ¨äºĨä¸Ģèµ·
    -0.06
    <![
    -0.06
    POSITIVE LOGITS
    üg
    0.08
    anko
    0.08
     ('
    0.08
    ÑĢенд
    0.07
    andler
    0.07
    nof
    0.07
    igans
    0.07
    ugno
    0.07
    inz
    0.07
    antly
    0.07
    Activations Density 0.140%

    No Known Activations