© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Qwen3-1.7B
    3. 27-LLAMASCOPE-2-LORSA-16K-K64
    4. 16158
    Prev
    Next
    INDEX
    Explanations

    say ix

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

    No Comments

    Negative Logits
    andin
    -20.25
    arian
    -18.75
    okane
    -18.63
     LPC
    -17.88
    ари
    -17.38
    anan
    -17.13
    olan
    -17.00
    avad
    -16.75
    alin
    -16.63
    iele
    -16.50
    POSITIVE LOGITS
     twe
    18.00
     Jens
    17.75
    伍
    16.88
     cubes
    16.75
    AXB
    16.13
    	pw
    16.00
    加密
    15.75
    mw
    15.44
     cubic
    15.44
    wort
    15.44
    Activations Density 0.001%

    No Known Activations