© 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. 7401
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    纸ä¸Ĭ
    -0.07
    деб
    -0.07
    -pdf
    -0.06
    å½ĵå±ŀ
    -0.06
    æ¯Ķä½ł
    -0.06
    accio
    -0.06
    ä¸ŃåĽ½äººæ°ij
    -0.06
    ochond
    -0.06
     Sacr
    -0.06
    دد
    -0.06
    POSITIVE LOGITS
    é«ĺ度
    0.08
    erten
    0.08
    geno
    0.08
    árt
    0.08
    ä¿¡æľį
    0.07
    aira
    0.07
    hart
    0.07
    éħ£
    0.07
    çĥĪ
    0.07
    orat
    0.07
    Activations Density 0.000%

    No Known Activations