© 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. 58246
    Prev
    Next
    INDEX
    Explanations

    semiconductor physics and chemistry

    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
     Lions
    -0.08
     unt
    -0.07
    çī¹åĭĴ
    -0.07
    omen
    -0.07
    çĭ®
    -0.07
    ptos
    -0.07
    çĤľ
    -0.06
    çĦĸ
    -0.06
     lions
    -0.06
    unt
    -0.06
    POSITIVE LOGITS
     formation
    0.09
    interop
    0.08
     composed
    0.08
    累累
    0.08
     formed
    0.07
     Formation
    0.07
    纨
    0.07
    eking
    0.07
    subclass
    0.07
     COLLECTION
    0.07
    Activations Density 0.006%

    No Known Activations