© 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. 2856
    Prev
    Next
    INDEX
    Explanations

    say tmp

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

    No Comments

    Negative Logits
    pet
    -17.50
    套
    -16.13
     Pet
    -15.94
    apos
    -15.94
     pet
    -15.88
    eton
    -15.44
     Annotation
    -15.19
    vis
    -15.13
     Petr
    -14.63
    _et
    -14.50
    POSITIVE LOGITS
     tmp
    60.25
    =tmp
    55.75
    [tmp
    54.75
    (tmp
    53.75
    tmp
    52.75
    ,tmp
    52.25
    	tmp
    51.75
    _tmp
    44.25
    .tmp
    43.25
    Tmp
    41.75
    Activations Density 0.020%

    No Known Activations