© 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. 15135
    Prev
    Next
    INDEX
    Explanations

    chromatin fibers

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

    No Comments

    Negative Logits
    敕
    -16.13
     defe
    -15.69
    (listener
    -15.31
    泄漏
    -15.00
    崆
    -14.88
     Killer
    -14.50
    riere
    -14.38
    [at
    -14.25
    砒
    -14.25
    aney
    -14.00
    POSITIVE LOGITS
    주시
    14.50
    rels
    14.44
    irms
    14.44
     rel
    14.44
    Pixels
    14.44
    fraction
    14.19
    政治
    14.19
    Double
    14.06
    strained
    13.75
     Political
    13.69
    Activations Density 0.044%

    No Known Activations