© 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. 2479
    Prev
    Next
    INDEX
    Explanations

    say perm

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

    No Comments

    Negative Logits
    �
    -17.50
    Mil
    -16.63
    Ctx
    -16.50
    (util
    -16.38
     Vis
    -15.56
    套
    -15.38
     š
    -15.19
     regime
    -14.81
     Erin
    -14.75
    (Util
    -14.63
    POSITIVE LOGITS
     perm
    38.75
    Perm
    36.75
    perm
    36.75
     Perm
    34.25
    _perm
    34.00
    永久
    33.25
    .perm
    32.75
    perms
    32.25
    Permanent
    32.25
     Permanent
    32.25
    Activations Density 0.097%

    No Known Activations