© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 17090
    Prev
    Next
    INDEX
    Explanations

    action adverbs

    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
    å°ĸåı«
    -0.08
     scream
    -0.08
    羡
    -0.07
    akil
    -0.06
    åĽĬ
    -0.06
    erver
    -0.06
    ard
    -0.06
    å¦ĤæľīçĸijéĹ®
    -0.06
    è¾ķ
    -0.06
     screamed
    -0.06
    POSITIVE LOGITS
    uesa
    0.09
    iglia
    0.08
     Elabor
    0.08
    änner
    0.08
    )::
    0.08
    è¿Ļ个éĹ®é¢ĺçļĦ
    0.08
    سد
    0.07
    mooth
    0.07
    磼
    0.07
    ény
    0.07
    Activations Density 0.019%

    No Known Activations