© 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. 2008
    Prev
    Next
    INDEX
    Explanations

    do not say radio

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

    No Comments

    Negative Logits
     Radio
    -37.75
     radio
    -37.50
    radio
    -37.00
    Radio
    -36.75
     RADIO
    -34.50
    _RADIO
    -34.00
     radios
    -33.75
     Radiation
    -32.75
    -radio
    -31.75
     radioactive
    -31.50
    POSITIVE LOGITS
    Python
    19.25
     Python
    18.50
     python
    15.69
    python
    14.94
    .Networking
    14.19
    hips
    13.31
    Eth
    12.94
    皮
    12.88
    .eth
    12.81
    uce
    12.56
    Activations Density 0.108%

    No Known Activations