© 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. 15620
    Prev
    Next
    INDEX
    Explanations

    say "-a" suffix

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

    No Comments

    Negative Logits
    crypt
    -18.63
    黍
    -17.88
     Trident
    -17.75
    ichert
    -17.38
     Lindsey
    -17.38
    beck
    -17.38
    甬
    -17.25
     Covenant
    -17.13
    锲
    -16.75
    遴
    -16.63
    POSITIVE LOGITS
    (ra
    32.00
    .ra
    29.88
    asa
    29.50
    oka
    29.00
    sa
    29.00
    ra
    28.75
    aura
    28.75
    ssa
    28.63
    .ga
    28.38
    sta
    28.25
    Activations Density 3.969%

    No Known Activations