© 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. 64343
    Prev
    Next
    INDEX
    Explanations

    file path separators

    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
    allas
    -0.07
     ma
    -0.06
     extended
    -0.06
    ä½ľåĵģåĨħ容
    -0.06
    å°¼åħĭ
    -0.06
    _k
    -0.06
    为该
    -0.06
     skyl
    -0.06
    --------------------------------------------------------------------------------
    -0.06
     ввод
    -0.06
    POSITIVE LOGITS
     **.**
    0.10
    ingan
    0.08
    æľĿå¤ķ
    0.08
     **:**
    0.08
     *.*
    0.07
    roku
    0.07
    issons
    0.07
    attan
    0.07
    iems
    0.07
    _regularizer
    0.07
    Activations Density 0.004%

    No Known Activations