© 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. 14853
    Prev
    Next
    INDEX
    Explanations

    no premature

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

    No Comments

    Negative Logits
    r
    -21.50
     r
    -21.50
    reck
    -20.38
    reu
    -20.25
    RET
    -19.75
    ｒ
    -18.88
    р
    -18.63
    rett
    -18.50
    T
    -18.13
    rest
    -17.75
    POSITIVE LOGITS
    dq
    20.25
     dq
    19.75
    qb
    19.13
    .nz
    18.50
    qn
    18.25
    enan
    18.00
    VICE
    17.75
    avicon
    17.63
     Hornets
    17.25
    ique
    17.13
    Activations Density 0.511%

    No Known Activations