© 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. 30741
    Prev
    Next
    INDEX
    Explanations

    specified location

    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
    俨
    -0.08
    ackers
    -0.07
    éĩij森
    -0.07
    æĻ®æ£®
    -0.07
    -array
    -0.07
    lan
    -0.07
     <![
    -0.07
    ä¸Ĭè¿°äºĭå®ŀ
    -0.07
    çĭ¬ä¸ĢæĹłäºĮ
    -0.07
    ×Ĺ×ķת
    -0.07
    POSITIVE LOGITS
     specified
    0.14
    æĮĩå®ļçļĦ
    0.12
     prescribed
    0.12
    æĮĩå®ļ
    0.12
    è§Ħå®ļ
    0.11
     promised
    0.11
    specified
    0.11
    è§Ħå®ļçļĦ
    0.11
     stip
    0.10
    è¦ģæ±ĤçļĦ
    0.09
    Activations Density 0.447%

    No Known Activations