© 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. 27-LLAMASCOPE-2-LORSA-16K-K64
    7. 15152
    Prev
    Next
    INDEX
    Explanations

    say numbers

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

    No Comments

    Negative Logits
    ei
    -19.63
    eo
    -19.00
    enne
    -19.00
    eon
    -18.63
    ae
    -17.88
    ecycle
    -17.63
    oons
    -17.38
    ef
    -16.88
    ono
    -16.50
    eos
    -16.50
    POSITIVE LOGITS
    .dds
    17.50
     decking
    16.63
     Ded
    16.50
    �
    15.50
     cad
    15.38
    ;d
    15.13
     kart
    14.75
    dw
    14.69
     viewType
    14.56
    dx
    14.50
    Activations Density 0.037%

    No Known Activations