© 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. 15217
    Prev
    Next
    INDEX
    Explanations

    county names

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

    No Comments

    Negative Logits
     di
    -22.25
    甸
    -20.00
    (di
    -19.63
    -di
    -18.63
    di
    -18.38
    odi
    -18.25
    _DI
    -18.13
     stretched
    -18.00
     ди
    -17.88
    EDI
    -17.25
    POSITIVE LOGITS
    kon
    18.25
    kt
    17.38
     pro
    17.13
     kon
    16.13
     про
    15.69
    chner
    15.31
    sez
    15.31
    ks
    14.38
     Kon
    14.38
    CON
    14.31
    Activations Density 0.496%

    No Known Activations