© 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. 14646
    Prev
    Next
    INDEX
    Explanations

    [steps] => [.]

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

    No Comments

    Negative Logits
    [".
    -14.25
    FAULT
    -14.13
    зов
    -13.63
    飛
    -13.13
    -mail
    -12.94
    £o
    -12.81
    'label
    -12.50
    tn
    -12.44
    sonian
    -12.44
    FieldType
    -12.38
    POSITIVE LOGITS
    yna
    16.88
    ubi
    16.50
    ippers
    16.50
    alus
    16.00
    anst
    15.88
    inium
    15.38
    .abstract
    15.13
    icer
    14.56
    ubber
    14.38
    als
    14.31
    Activations Density 0.002%

    No Known Activations