© 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. 15270
    Prev
    Next
    INDEX
    Explanations

    say "8"

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

    No Comments

    Negative Logits
    _routes
    -16.38
    orz
    -16.13
     spender
    -15.06
    furt
    -14.88
    lation
    -14.44
    ��
    -14.38
    elman
    -14.31
    uzzer
    -14.31
    uration
    -14.00
    rary
    -13.88
    POSITIVE LOGITS
    .hm
    14.75
     deluxe
    14.50
    �
    13.25
     ATV
    13.25
     право
    13.19
    .ss
    12.81
    enna
    12.81
    技师
    12.69
    讪
    12.56
    ძ
    12.44
    Activations Density 0.026%

    No Known Activations