© 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. 46336
    Prev
    Next
    INDEX
    Explanations

    panel's, tank cover, mold with, driving means

    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
    uos
    -0.08
    rin
    -0.08
    boll
    -0.07
    otten
    -0.07
    äºļ
    -0.07
    eos
    -0.07
     VIA
    -0.07
    asion
    -0.07
    _FLASH
    -0.07
     Polis
    -0.07
    POSITIVE LOGITS
    对ä»ĸ们
    0.08
    对ä»ĸ们çļĦ
    0.08
    对ä»ĸ
    0.08
    对å®ĥ
    0.08
    istol
    0.07
    对åħ¶
    0.07
    对ä»ĸçļĦ
    0.07
    å°įä»ĸ
    0.07
    æĺ¯åħ¶
    0.07
     عÙĨÙĩÙħ
    0.07
    Activations Density 0.236%

    No Known Activations