© 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. 2379
    Prev
    Next
    INDEX
    Explanations

    say base

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

    No Comments

    Negative Logits
    PROP
    -21.50
    Mor
    -21.50
     propositions
    -21.13
     proposition
    -21.00
     Proposition
    -19.50
    NUM
    -18.88
    Prop
    -18.50
     PROP
    -18.38
     Prop
    -18.25
     mor
    -17.88
    POSITIVE LOGITS
    基
    57.00
     Bas
    48.00
     bas
    45.00
    Bas
    36.00
     baseline
    36.00
    Baseline
    34.00
    bas
    30.63
    baseline
    30.25
     basal
    29.50
    _baseline
    26.13
    Activations Density 0.142%

    No Known Activations