© 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. 25588
    Prev
    Next
    INDEX
    Explanations

    internal class

    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
    -0.09
    缸è¾ħ缸æĪIJ
    -0.09
    ation
    -0.08
    ×ķ
    -0.08
    roup
    -0.08
    a
    -0.07
    iness
    -0.07
    matic
    -0.07
    antine
    -0.07
    ़
    -0.07
    POSITIVE LOGITS
    å¤ĸçļĦ
    0.12
    ities
    0.11
    çĸļ
    0.11
    most
    0.10
    æĶ¿éĥ¨
    0.10
    سÙĬر
    0.09
    ׼×ķף
    0.09
    è§Ĩéķľ
    0.09
    çijŀæĭī
    0.08
    uke
    0.08
    Activations Density 0.004%

    No Known Activations