© 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. 62399
    Prev
    Next
    INDEX
    Explanations

    percentages

    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
    kers
    -0.07
    ())),
    -0.07
    elves
    -0.07
     ØŃاÙĦÙĬا
    -0.07
    éĩ
    -0.07
    ê°ģ
    -0.07
    cef
    -0.06
     }),
    -0.06
     now
    -0.06
     ordinaria
    -0.06
    POSITIVE LOGITS
    å½ĵæŶ
    0.08
    åľ¨å½ĵæŶ
    0.08
    jakan
    0.08
    å½ĵæŶçļĦ
    0.08
     damals
    0.07
    åĬĽéĩıçļĦ
    0.07
     volna
    0.07
    <|box_end|>
    0.07
    оÑĩе
    0.07
    .inspect
    0.07
    Activations Density 0.132%

    No Known Activations