© 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. 14937
    Prev
    Next
    INDEX
    Explanations

    F‑starting words

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

    No Comments

    Negative Logits
     lobster
    -22.88
     tô
    -22.50
    琅
    -22.38
    リン
    -21.00
     Lov
    -20.88
     Stout
    -19.50
    洛
    -19.25
    黎
    -19.13
    虹
    -19.00
    浏
    -19.00
    POSITIVE LOGITS
     di
    20.50
    -di
    15.88
    (di
    15.31
    Di
    15.06
     Chapman
    14.63
     Di
    14.44
    ment
    14.38
    trs
    13.88
    di
    13.75
    HP
    13.38
    Activations Density 0.020%

    No Known Activations