© 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. 64320
    Prev
    Next
    INDEX
    Explanations

    proper nouns and names

    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
    çļĦ
    -0.10
    istic
    -0.09
    èĩªå·±
    -0.08
    ../../../
    -0.08
    heits
    -0.08
    /or
    -0.08
    ìį¨
    -0.08
    à§įস
    -0.08
    stüt
    -0.08
    ÑģÑı
    -0.08
    POSITIVE LOGITS
    Ø©
    0.14
    åĭĩå¾Ģ缴åīį
    0.08
    incontro
    0.08
    ting
    0.08
    anja
    0.08
    缸è¾ħ缸æĪIJ
    0.08
    eck
    0.08
    人æĿ¥è¯´
    0.08
    anje
    0.07
    raine
    0.07
    Activations Density 0.003%

    No Known Activations