© 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. 14456
    Prev
    Next
    INDEX
    Explanations

    names

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

    No Comments

    Negative Logits
     Central
    -17.38
    dia
    -17.13
    ods
    -16.25
    etsk
    -16.25
     Punch
    -15.69
    lags
    -15.69
    izona
    -15.63
    崆
    -15.63
    ivia
    -15.56
    Central
    -15.56
    POSITIVE LOGITS
    塑
    16.25
    叙事
    15.88
     reels
    15.13
    嗓
    14.94
    射
    14.75
     Narr
    14.69
    ucc
    14.38
     narr
    14.38
    农牧
    14.06
     rex
    13.75
    Activations Density 0.801%

    No Known Activations