© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-1.7B
    5. 27-LLAMASCOPE-2-LORSA-16K-K64
    7. 14798
    Prev
    Next
    INDEX
    Explanations

    post‑newline token

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

    No Comments

    Negative Logits
     đông
    -15.63
    dio
    -15.06
    ixo
    -15.06
    COPE
    -15.00
     enlisted
    -14.75
    霹
    -14.63
     Sandwich
    -14.25
    -eye
    -14.19
     binder
    -14.06
     stir
    -13.56
    POSITIVE LOGITS
    hone
    15.25
     bright
    15.25
    毛泽
    14.94
    apon
    14.44
     than
    14.25
    than
    14.19
     sale
    14.00
    瘗
    14.00
    odes
    14.00
     ApiException
    13.94
    Activations Density 0.705%

    No Known Activations