© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-1.7B
    5. 27-LLAMASCOPE-2-LORSA-16K-K64
    7. 14574
    Prev
    Next
    INDEX
    Explanations

    New‑ place names

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

    No Comments

    Negative Logits
    蹑
    -18.00
    建筑师
    -17.00
    _MR
    -16.88
    灰
    -16.38
    TEAM
    -16.38
    _VIS
    -16.38
     NOI
    -16.13
    设计师
    -16.13
    IRS
    -16.00
    访
    -16.00
    POSITIVE LOGITS
    ork
    20.63
    agen
    17.00
    worth
    15.31
    ourt
    15.00
    ether
    14.31
    ductory
    14.19
    ron
    13.75
    psilon
    13.69
     witness
    13.50
    ât
    13.50
    Activations Density 0.030%

    No Known Activations