© 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. 18455
    Prev
    Next
    INDEX
    Explanations

    accelerating, enhancing, or suppressive effects

    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
     either
    -0.08
    kel
    -0.07
    endorf
    -0.07
    ãģĶ
    -0.06
    dar
    -0.06
    æĹłä»»ä½ķ
    -0.06
    ik
    -0.06
    è¦ģä¹Ī
    -0.06
    klär
    -0.06
    chal
    -0.06
    POSITIVE LOGITS
    umbs
    0.09
    æĪĸå°ij
    0.08
    idot
    0.08
    mdb
    0.08
    åħ¬æīĢ
    0.08
    odom
    0.08
    åį´åľ¨
    0.08
    请ä¸İæĪij们èģĶç³»
    0.07
    ä¸ģ
    0.07
    rase
    0.07
    Activations Density 0.250%

    No Known Activations