© 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. 2404
    Prev
    Next
    INDEX
    Explanations

    iter

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

    No Comments

    Negative Logits
     �
    -15.75
    þ
    -15.00
    _simulation
    -14.63
     Mun
    -14.38
    tü
    -14.00
    enheim
    -13.94
    颖
    -13.69
    ＝
    -13.56
     Eugene
    -13.50
    generation
    -13.31
    POSITIVE LOGITS
     iter
    38.00
    iter
    35.00
    	iter
    34.25
     ter
    27.50
    Iter
    25.50
    ter
    22.75
    _iter
    22.50
    Ter
    22.13
     Mer
    22.00
    (iter
    21.38
    Activations Density 0.006%

    No Known Activations