© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 40559
    Prev
    Next
    INDEX
    Explanations

    linguistic structure and rules

    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
    ucha
    -0.08
     contemplated
    -0.08
    iscal
    -0.07
    éľĢè¦ģä½ł
    -0.07
    iore
    -0.07
    veno
    -0.07
    åįİåķĨ
    -0.07
     conv
    -0.07
    ä¸ŃæĪIJèį¯
    -0.07
    akit
    -0.07
    POSITIVE LOGITS
     stylist
    0.10
     synt
    0.09
     structural
    0.09
     rules
    0.08
    è§ĦåĪĻ
    0.08
     rule
    0.08
     corpus
    0.08
    линг
    0.08
    rules
    0.08
    -rule
    0.08
    Activations Density 0.077%

    No Known Activations