© 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. 15381
    Prev
    Next
    INDEX
    Explanations

    say "geology"

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

    No Comments

    Negative Logits
    Cpp
    -17.38
    醺
    -17.13
    苏宁
    -16.63
     douche
    -16.50
    _DSP
    -16.38
     Bourbon
    -16.25
    PWM
    -16.13
    痿
    -15.81
    惆
    -15.56
    CppType
    -15.44
    POSITIVE LOGITS
     geological
    38.00
    地质
    37.00
     ge
    36.00
     geom
    35.25
    Ge
    35.25
     Ge
    34.50
    地理
    34.50
    _ge
    33.75
    .Ge
    33.00
    ge
    32.75
    Activations Density 0.236%

    No Known Activations