© 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. 7674
    Prev
    Next
    INDEX
    Explanations

    buckyballs, fullerenes, clusters, cages, hexagonal

    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
    æĮŁ
    -0.07
     Fargo
    -0.07
    ç³ľçĥĤ
    -0.06
    æŧ
    -0.06
    æī¬
    -0.06
    éľĸ
    -0.06
    -assets
    -0.06
    auled
    -0.06
    è¦ģè·Ł
    -0.06
    Multiplier
    -0.06
    POSITIVE LOGITS
    agon
    0.08
    icos
    0.08
     tess
    0.08
    å°ģ顶
    0.08
    SIZE
    0.08
    _doc
    0.08
     clusters
    0.08
    ä¸īåįģåħŃ
    0.08
     composition
    0.08
     hex
    0.08
    Activations Density 0.053%

    No Known Activations