© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-1.7B
    5. 27-LLAMASCOPE-2-LORSA-16K-K64
    7. 14386
    Prev
    Next
    INDEX
    Explanations

    hex identifiers

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

    No Comments

    Negative Logits
    adge
    -21.38
    cki
    -20.38
     Bicycle
    -20.25
    woke
    -19.13
    abby
    -19.00
    ächt
    -19.00
    dge
    -18.88
    abay
    -18.63
     Bek
    -18.38
     candles
    -18.25
    POSITIVE LOGITS
     lex
    17.13
     pol
    15.38
    pol
    15.31
     sl
    15.00
     res
    14.69
     polit
    14.44
    Sl
    14.38
     s
    14.19
     mor
    14.06
     Nz
    14.06
    Activations Density 0.079%

    No Known Activations