© 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. 15112
    Prev
    Next
    INDEX
    Explanations

    year numbers

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

    No Comments

    Negative Logits
    um
    -14.88
     apolog
    -14.63
     IPA
    -14.13
     Mot
    -13.88
     neon
    -13.25
    erce
    -13.19
    原谅
    -13.06
    ormal
    -12.94
    ozilla
    -12.94
    urve
    -12.81
    POSITIVE LOGITS
    sek
    18.75
    Sensitive
    17.25
     childs
    16.00
    phan
    15.69
    SetValue
    15.31
    DS
    15.19
    敏感
    15.06
    _ds
    14.94
     Chase
    14.88
    ECH
    14.81
    Activations Density 0.024%

    No Known Activations