© 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. 26-LLAMASCOPE-2-LORSA-16K-K64
    7. 2394
    Prev
    Next
    INDEX
    Explanations

    say "ment" words

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

    No Comments

    Negative Logits
    (poly
    -23.00
    _poly
    -22.50
    poly
    -19.88
    .poly
    -18.88
    Poly
    -18.75
     poly
    -18.13
     Poly
    -17.38
     polymer
    -17.13
     polynomial
    -16.75
     Filme
    -16.50
    POSITIVE LOGITS
     ment
    38.75
     Ment
    36.50
     mentor
    34.50
     mentors
    33.75
     mentoring
    32.50
    ment
    32.25
    mentor
    30.88
     Mentor
    30.00
    MENT
    28.50
    _ment
    24.75
    Activations Density 0.028%

    No Known Activations