© 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. 2417
    Prev
    Next
    INDEX
    Explanations

    say def

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

    No Comments

    Negative Logits
    商
    -16.38
    _MAG
    -16.25
    Jer
    -15.44
    bery
    -14.19
    ʰ
    -14.06
    .addObject
    -13.88
    _pat
    -13.69
    pat
    -13.56
    PAT
    -13.38
    殷
    -13.19
    POSITIVE LOGITS
     def
    78.50
    	def
    57.75
    def
    57.50
     Def
    55.25
    Def
    50.50
    (def
    48.75
    .def
    47.75
    -def
    46.25
    _def
    44.00
     deflect
    43.50
    Activations Density 0.146%

    No Known Activations