© 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. 62057
    Prev
    Next
    INDEX
    Explanations

    years dates citation numbers

    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
     \
    -0.06
    æĬµ
    -0.06
    ++
    -0.06
     boosted
    -0.06
    她便
    -0.05
     contained
    -0.05
    ×£
    -0.05
     =
    -0.05
     badge
    -0.05
    åĢ
    -0.05
    POSITIVE LOGITS
    篤
    0.08
    manship
    0.08
    éĶ¦æłĩ
    0.08
    èĻĶ
    0.08
    å¤§ä½ľ
    0.08
    ilen
    0.07
    ilog
    0.07
    Ïģθ
    0.07
    æĮĩ示精ç¥ŀ
    0.07
     Docs
    0.07
    Activations Density 0.113%

    No Known Activations