© 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. 2600
    Prev
    Next
    INDEX
    Explanations

    say "exp" words

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

    No Comments

    Negative Logits
     msg
    -21.75
    (msg
    -21.13
    秧
    -20.75
    =msg
    -20.38
     Ty
    -20.13
    壬
    -19.25
     sims
    -19.00
    ,msg
    -19.00
    /msg
    -18.63
    msg
    -18.00
    POSITIVE LOGITS
     exploit
    41.00
     exploited
    37.00
    利
    36.00
     exploitation
    34.25
    explo
    33.50
     exploiting
    32.50
     exploits
    30.88
     explo
    30.50
     Exp
    26.75
    Exp
    25.25
    Activations Density 0.080%

    No Known Activations