© 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. 15171
    Prev
    Next
    INDEX
    Explanations

    say K

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

    No Comments

    Negative Logits
    alog
    -16.88
    lass
    -16.25
    ads
    -15.75
    ZH
    -15.63
    adle
    -15.44
    Ồ
    -15.44
    lug
    -15.38
     Baghdad
    -15.31
    AdapterManager
    -15.19
    alous
    -15.06
    POSITIVE LOGITS
    KV
    19.00
     K
    18.63
    K
    18.63
    KS
    18.50
    _kv
    18.00
     k
    17.38
    KT
    17.25
    _K
    17.13
    estone
    16.63
    kek
    16.25
    Activations Density 0.319%

    No Known Activations