© 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. 21647
    Prev
    Next
    INDEX
    Explanations

    data structures

    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
     escalate
    -0.10
     hardcoded
    -0.09
     upto
    -0.08
     admittedly
    -0.08
     ironically
    -0.08
     hopefully
    -0.08
    anon
    -0.07
     nonzero
    -0.07
     ephem
    -0.07
     onwards
    -0.07
    POSITIVE LOGITS
    âĢij
    0.09
    ).-
    0.09
     bila
    0.08
    檬
    0.07
    ç»®
    0.07
    å«©çļĦ
    0.06
    æļĩ
    0.06
    )=>
    0.06
    æµ·æ¶Ľ
    0.06
    婧
    0.06
    Activations Density 0.007%

    No Known Activations