© 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. 1630
    Prev
    Next
    INDEX
    Explanations

    implicitly or naturally

    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
    indra
    -0.07
    наÑĢ
    -0.07
    ëĩ
    -0.07
    anagan
    -0.07
    epen
    -0.07
    iaan
    -0.07
    ШÐIJ
    -0.07
    |M
    -0.07
    âĵĴ
    -0.07
    çŁ¯
    -0.07
    POSITIVE LOGITS
     implicitly
    0.13
     implicit
    0.12
    implicitly
    0.12
    Implicit
    0.11
    -like
    0.11
     Implicit
    0.11
    天çĦ¶çļĦ
    0.11
    èĩªåıij
    0.10
    天çĦ¶
    0.10
     naturally
    0.10
    Activations Density 0.341%

    No Known Activations