© 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. 27862
    Prev
    Next
    INDEX
    Explanations

    rupture or perforation

    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
    orch
    -0.07
    å¨ĩ妻
    -0.07
    èĢ½
    -0.07
    ç½®ãģį
    -0.07
    åĵº
    -0.07
    bourne
    -0.07
    éĢ¼äºº
    -0.06
    ä¸įåĩı
    -0.06
    ombres
    -0.06
    isle
    -0.06
    POSITIVE LOGITS
    çł´è£Ĥ
    0.15
     rupt
    0.13
    çł´
    0.13
     rupture
    0.12
    çł´äºĨ
    0.12
    -open
    0.11
    ä¸įçł´
    0.11
     openings
    0.11
     breaches
    0.11
    è£Ĥ
    0.11
    Activations Density 0.136%

    No Known Activations