© 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. 45789
    Prev
    Next
    INDEX
    Explanations

    investigate, describe, discuss

    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
    æĪĸèĢħæľī
    -0.07
    ä»ĸäºĨ
    -0.07
    åħ¹
    -0.07
    å°±çľĭ
    -0.07
     shown
    -0.07
    اء
    -0.07
    游æĪıä»ĭç»į
    -0.06
    æĪijäºĨ
    -0.06
    她äºĨ
    -0.06
     anymore
    -0.06
    POSITIVE LOGITS
    åħ¶åľ¨
    0.08
     corresponding
    0.08
    åħ¶å¯¹
    0.08
    iknya
    0.08
    ANTA
    0.08
    +%
    0.07
    ardy
    0.07
    ardini
    0.07
    ¾
    0.07
    iglich
    0.07
    Activations Density 0.079%

    No Known Activations