© 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. 8076
    Prev
    Next
    INDEX
    Explanations

    exceeds or surpasses

    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
    utel
    -0.07
    ownt
    -0.07
    ossed
    -0.06
    ä½Ĩ以
    -0.06
    oden
    -0.06
    Patch
    -0.06
     Trace
    -0.06
    åįĵ
    -0.06
    eh
    -0.06
    èĭij
    -0.06
    POSITIVE LOGITS
     exceeds
    0.10
    è¶ħè¿ĩäºĨ
    0.10
     melebihi
    0.10
     supera
    0.10
    ä¸įèĥ½è¶ħè¿ĩ
    0.10
     пÑĢевÑĭÑĪаеÑĤ
    0.10
     exceed
    0.10
     surpass
    0.09
    å·²ç»ıè¶ħè¿ĩ
    0.08
    è¶ħåĩºäºĨ
    0.08
    Activations Density 0.086%

    No Known Activations