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

    Neuronpedia

    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. 15686
    Prev
    Next
    INDEX
    Explanations

    say "3"

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

    No Comments

    Negative Logits
     TRANS
    -19.63
    TRANS
    -18.25
    -trans
    -17.25
    笺
    -17.25
     Trans
    -17.25
    trans
    -16.75
    Trans
    -16.63
    (Photo
    -16.50
    _trans
    -16.00
    emodel
    -15.94
    POSITIVE LOGITS
    막
    16.38
     курс
    16.00
    Курс
    15.25
    iid
    14.56
    LI
    14.56
    IX
    14.56
    iq
    14.50
    unds
    14.31
    记忆力
    14.25
    HX
    14.19
    Activations Density 0.007%

    No Known Activations