© 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. 15998
    Prev
    Next
    INDEX
    Explanations

    say conc

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

    No Comments

    Negative Logits
     Greenwood
    -25.50
    青山
    -24.50
     Roose
    -20.75
     Johan
    -20.63
    安娜
    -20.38
     Sapphire
    -20.00
    路虎
    -20.00
    堇
    -19.88
     Cardiff
    -19.25
    _blueprint
    -19.25
    POSITIVE LOGITS
    conc
    24.75
    _CONV
    23.75
     conc
    23.75
     Conc
    23.63
    /con
    22.25
    conv
    21.75
    (con
    21.63
    lé
    21.38
     kon
    21.13
    (conv
    20.88
    Activations Density 4.613%

    No Known Activations