© 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. 15231
    Prev
    Next
    INDEX
    Explanations

    [di] => [di]

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

    No Comments

    Negative Logits
    xff
    -19.63
    .Diff
    -18.38
    jem
    -18.38
    diff
    -18.13
    	diff
    -17.88
    iron
    -17.13
    ffc
    -17.00
    itim
    -16.88
     Diff
    -16.38
    强者
    -16.38
    POSITIVE LOGITS
     di
    19.63
     Di
    17.50
    ei
    15.88
    _di
    15.75
     vers
    15.75
    Di
    15.56
    (di
    14.94
    逆势
    14.75
    ina
    14.56
    .Di
    14.56
    Activations Density 0.461%

    No Known Activations