© 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. 62771
    Prev
    Next
    INDEX
    Explanations

    period followed by a new sentence start

    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
    prod
    -0.08
    åıªè¦ģä½ł
    -0.07
    prob
    -0.07
    åĽŀ羸
    -0.06
    isher
    -0.06
    ìŀĶ
    -0.06
    ìķĦ
    -0.06
    ish
    -0.06
    å§ļæĺİ
    -0.06
     Tow
    -0.06
    POSITIVE LOGITS
    èŀįèŀį
    0.08
    ä¸ĢæŶéĹ´
    0.08
     chôm
    0.08
    )[-
    0.08
     bì
    0.08
    uzz
    0.08
    itis
    0.08
    ÑĤип
    0.07
     Alley
    0.07
    çijŁ
    0.07
    Activations Density 0.020%

    No Known Activations