© 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. 15313
    Prev
    Next
    INDEX
    Explanations

    say G words

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

    No Comments

    Negative Logits
     Lod
    -22.50
    oref
    -21.75
     LDS
    -21.00
    _rho
    -19.88
    ombo
    -19.00
     Caj
    -19.00
    リン
    -18.88
    loff
    -18.75
     lob
    -18.38
    lod
    -18.25
    POSITIVE LOGITS
     di
    16.50
    sw
    15.75
     Di
    14.63
    SW
    14.50
    @Spring
    14.31
    atin
    14.19
    Di
    13.81
    SWG
    13.81
    ismic
    13.75
    hw
    13.69
    Activations Density 0.014%

    No Known Activations