© 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. 41902
    Prev
    Next
    INDEX
    Explanations

    insoluble precipitation

    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
     pÅĤyn
    -0.07
     getArguments
    -0.07
    running
    -0.07
    erto
    -0.07
    å¹ħ度
    -0.07
    Running
    -0.06
    çĵ¤
    -0.06
    åħħæ²Ľ
    -0.06
     womb
    -0.06
    éĢıæĶ¯
    -0.06
    POSITIVE LOGITS
     insol
    0.10
     precip
    0.09
    ç»ĵ
    0.09
    itele
    0.09
    åłµä½ı
    0.09
     Insol
    0.08
     formation
    0.08
    .prevent
    0.08
    为éļ¾
    0.08
    çµIJ
    0.08
    Activations Density 0.012%

    No Known Activations