© 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. 16829
    Prev
    Next
    INDEX
    Explanations

    osteoporosis, fracture, weakened, reparative

    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
    zip
    -0.08
    keen
    -0.07
    姻ç¼ĺ
    -0.07
    пÑĤ
    -0.07
    ancestor
    -0.07
    داث
    -0.07
    nodeValue
    -0.07
     Zip
    -0.07
    çİ°åľºç¡®è®¤
    -0.07
    è¿Ľæł¡åĽŃ
    -0.07
    POSITIVE LOGITS
    èĻļå¼±
    0.12
     frail
    0.09
     weakness
    0.09
    æĹłåĬĽ
    0.09
    æī¶
    0.08
    è¡°å¼±
    0.08
     debil
    0.08
    æĺ¯çľŁ
    0.08
    æī¶åĬ©
    0.07
    å¼±
    0.07
    Activations Density 0.001%

    No Known Activations