© 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. 33089
    Prev
    Next
    INDEX
    Explanations

    code blocks and definitions

    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
    å»ĵ
    -0.07
    plete
    -0.07
    isa
    -0.06
    t
    -0.06
    ãĥ¼ãĥ«ãģ®
    -0.06
     v
    -0.06
    æ¯ıåĪ°
    -0.06
    çµ®
    -0.06
    isse
    -0.06
    为
    -0.06
    POSITIVE LOGITS
    ode
    0.08
    Ø°ÙĬب
    0.08
    æĶ¶ä¸ĭ
    0.08
    (sq
    0.08
    edly
    0.08
    ALLY
    0.08
    çĭ¬èµĦ
    0.08
    schlä
    0.08
    ç¹ģ
    0.07
    éĩĮäºļ
    0.07
    Activations Density 0.083%

    No Known Activations