© 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. 14758
    Prev
    Next
    INDEX
    Explanations

    subword fragments

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

    No Comments

    Negative Logits
    di
    -17.63
    dic
    -17.25
     di
    -16.63
    源泉
    -16.00
    oric
    -16.00
    .di
    -16.00
    (di
    -15.81
     Diy
    -15.75
    oku
    -15.38
    OTH
    -14.81
    POSITIVE LOGITS
    protein
    16.63
    bfd
    16.50
    conv
    16.38
    iste
    16.38
    iffe
    16.00
    asn
    15.81
    son
    15.19
    殄
    15.19
    pe
    15.13
    _conv
    15.00
    Activations Density 0.385%

    No Known Activations