© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Qwen3-1.7B
    3. 27-LLAMASCOPE-2-LORSA-16K-K64
    4. 16050
    Prev
    Next
    INDEX
    Explanations

    [fragment] => [full]

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

    No Comments

    Negative Logits
    heits
    -15.44
     Wedding
    -13.25
    okit
    -13.19
    kır
    -13.13
    椅子
    -13.06
     quên
    -12.94
    bursement
    -12.94
    phan
    -12.88
    秣
    -12.88
    房贷
    -12.81
    POSITIVE LOGITS
    -t
    48.50
    -T
    41.75
    _t
    40.50
    +t
    39.50
    	td
    39.25
     t
    39.00
    /t
    38.75
    tid
    38.75
    =t
    38.50
    _ta
    38.50
    Activations Density 6.981%

    No Known Activations