© 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. 32007
    Prev
    Next
    INDEX
    Explanations

    spasm, spasticity, contraction, tension

    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
     écl
    -0.08
    planet
    -0.08
    æµĵéĥģ
    -0.07
     skim
    -0.07
    è¿ľäºĨ
    -0.07
    åĿ¦
    -0.07
    åķĨçļĦ
    -0.07
     nef
    -0.07
    åĴ³
    -0.07
    èī°è¾Ľ
    -0.07
    POSITIVE LOGITS
    åĥµç¡¬
    0.12
    çĹīæĮĽ
    0.12
    紧绷
    0.11
    æĶ¾æĿ¾
    0.11
     tension
    0.11
     twitch
    0.10
    èĤĮèĤī
    0.10
     tense
    0.10
     relaxation
    0.10
    ç»·
    0.10
    Activations Density 0.032%

    No Known Activations