© 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. 51324
    Prev
    Next
    INDEX
    Explanations

    specific locations and institutions

    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
    ama
    -0.08
    è¦ģåIJij
    -0.08
    æIJĵ
    -0.07
    å¾Ħ
    -0.07
    lick
    -0.07
    Ïģθ
    -0.07
    å±ħæĺĵ
    -0.07
    æľīæŶåĢĻ
    -0.07
    åł
    -0.07
    ä¸ĢæĭĽ
    -0.07
    POSITIVE LOGITS
    -specific
    0.08
    çĽĬ
    0.08
    ç«Ļç«Ļ
    0.08
    ä¸ĢåĪĩ
    0.08
     specific
    0.08
    çļĦåħ·ä½ĵæĥħåĨµ
    0.08
    åħ·ä½ĵ
    0.08
    pecific
    0.08
    åħ·é«Ķ
    0.08
    åħ·ä½ĵéĹ®é¢ĺ
    0.07
    Activations Density 0.322%

    No Known Activations