© 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. 24190
    Prev
    Next
    INDEX
    Explanations

    author opens, several melons

    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
    ரா
    -0.08
    icat
    -0.07
    æĢİä¹Īèµ°
    -0.07
    åĤĢ
    -0.07
    رÙĪت
    -0.07
    MASK
    -0.07
    èŁij
    -0.07
    eck
    -0.07
    æij¸çĿĢ
    -0.07
    eles
    -0.07
    POSITIVE LOGITS
    彦
    0.07
    igny
    0.07
    çIJ³
    0.07
    ahaya
    0.06
    亨
    0.06
     nameof
    0.06
    æ´Ľæĸ¯
    0.06
    åħ°
    0.06
    èĬĿ
    0.06
    å¥Īä½ķ
    0.06
    Activations Density 0.001%

    No Known Activations