© 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. 2134
    Prev
    Next
    INDEX
    Explanations

    say intelligence

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

    No Comments

    Negative Logits
     vec
    -21.63
    (vec
    -21.00
     Vec
    -20.13
    vec
    -18.75
     cond
    -18.50
    eta
    -18.38
    etr
    -18.00
    (Vec
    -17.75
    	vec
    -17.75
    etas
    -17.38
    POSITIVE LOGITS
    智
    36.25
    Int
    32.50
     intelligence
    32.25
     Int
    31.38
    intelligence
    31.13
    int
    30.38
     Intelligence
    30.38
    .int
    28.88
    /int
    28.25
    	Int
    28.25
    Activations Density 0.105%

    No Known Activations