© 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
    3. Qwen3-1.7B
    5. 27-LLAMASCOPE-2-LORSA-16K-K64
    7. 16030
    Prev
    Next
    INDEX
    Explanations

    author initials

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

    No Comments

    Negative Logits
    imid
    -15.44
    spb
    -14.81
    LETED
    -14.44
    倮
    -14.06
    罘
    -13.88
    蓑
    -13.88
    傈
    -13.31
    _CHARSET
    -13.25
    PB
    -13.25
    茱
    -13.00
    POSITIVE LOGITS
    -D
    39.00
    -d
    38.50
    DG
    36.25
    DD
    35.75
    DL
    35.25
    DK
    35.00
    DH
    35.00
    DS
    35.00
    DA
    34.75
    dk
    34.75
    Activations Density 7.212%

    No Known Activations