© 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. 14750
    Prev
    Next
    INDEX
    Explanations

    say "9"

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

    No Comments

    Negative Logits
    itol
    -19.75
    IMAL
    -18.75
    vine
    -17.63
    coles
    -17.50
     toilet
    -17.38
    辇
    -17.00
     Cer
    -17.00
    roman
    -16.75
     Nicol
    -16.75
    IAL
    -16.63
    POSITIVE LOGITS
    5
    16.88
    ５
    15.19
    6
    15.13
    stro
    15.06
    _sv
    14.69
    _sw
    14.69
    7
    14.56
    滑
    14.38
     Scotia
    14.31
    �
    14.06
    Activations Density 0.042%

    No Known Activations