© 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. Qwen3-1.7B
    5. 26-LLAMASCOPE-2-LORSA-16K-K64
    7. 1265
    Prev
    Next
    INDEX
    Explanations

    say philosophical

    unknown · unknown
    New Auto-Interp
    Top Features by Cosine Similarity
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    hash
    -24.00
    _hash
    -23.38
    Hash
    -23.00
     hash
    -22.88
     Hash
    -22.75
    .hash
    -22.50
    _HASH
    -22.25
    HASH
    -21.13
     hashes
    -20.88
    	hash
    -20.38
    POSITIVE LOGITS
     philosophical
    19.50
    哲学
    18.88
    阅读
    18.75
    agus
    18.00
     philosophy
    17.50
     Philosoph
    17.38
    Sensor
    17.13
     Buddhist
    16.88
    sensor
    16.75
     unread
    16.75
    Activations Density 0.434%

    No Known Activations