© 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. 15188
    Prev
    Next
    INDEX
    Explanations

    say "names"

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

    No Comments

    Negative Logits
    kle
    -19.38
    reeze
    -19.00
    kl
    -17.88
    .Pass
    -17.88
    otr
    -17.63
    otec
    -17.63
    eur
    -17.00
    ty
    -17.00
    eki
    -17.00
    об
    -16.88
    POSITIVE LOGITS
    ramework
    14.38
     matchmaking
    12.88
    $args
    12.69
     CLICK
    12.38
    $config
    12.13
    LineEdit
    11.94
     soundtrack
    11.75
    compose
    11.69
    脱颖而出
    11.63
     modifiers
    11.44
    Activations Density 0.220%

    No Known Activations