© 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. 14865
    Prev
    Next
    INDEX
    Explanations

    the + place names

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

    No Comments

    Negative Logits
    ума
    -19.50
    ú
    -19.38
    uma
    -17.88
    umas
    -17.88
     capac
    -17.63
    LLU
    -16.63
    _RF
    -16.63
    umed
    -16.38
    emploi
    -16.13
     Speakers
    -15.81
    POSITIVE LOGITS
    -paced
    12.44
    chè
    12.44
    [assembly
    11.81
     bullpen
    11.75
    谐
    11.44
     trò
    11.38
    處
    11.25
    ][]
    11.06
     Green
    11.06
     Mix
    10.94
    Activations Density 0.040%

    No Known Activations