© 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. 32120
    Prev
    Next
    INDEX
    Explanations

    concentration and pH

    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
    åħ½
    -0.08
    INLINE
    -0.07
    éľĨ
    -0.07
    exe
    -0.07
    aptor
    -0.07
    åħ¨ä½ĵåijĺå·¥
    -0.07
    omad
    -0.06
    utters
    -0.06
    éĤĢ
    -0.06
    abbo
    -0.06
    POSITIVE LOGITS
     concentrations
    0.09
     concentration
    0.09
    æµĵ度
    0.08
    æµĵ度çļĦ
    0.08
     конÑĨенÑĤÑĢа
    0.08
    æµĵ度为
    0.08
     koncentr
    0.08
    .factor
    0.07
     koncent
    0.07
    factor
    0.07
    Activations Density 0.003%

    No Known Activations