© 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. 2576
    Prev
    Next
    INDEX
    Explanations

    say "four"

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

    No Comments

    Negative Logits
    振
    -22.75
     tube
    -19.13
    Tube
    -18.88
     ep
    -18.38
    spec
    -18.38
     Phil
    -18.00
     Ep
    -17.38
     hyp
    -17.38
     Reggie
    -17.38
    Mel
    -17.00
    POSITIVE LOGITS
     tet
    38.25
     �
    36.25
    quad
    34.25
    四
    34.25
     quadr
    31.63
     Tet
    30.00
     quad
    29.75
     Oct
    28.38
    cur
    26.75
     cur
    26.63
    Activations Density 0.166%

    No Known Activations