© 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. 2399
    Prev
    Next
    INDEX
    Explanations

    say "valve"

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

    No Comments

    Negative Logits
     radios
    -22.13
     radio
    -20.63
    _radio
    -19.25
    radio
    -18.88
    镭
    -18.75
     Radio
    -18.50
    afari
    -18.25
     RADIO
    -18.13
    Radio
    -17.50
    .Scan
    -17.50
    POSITIVE LOGITS
     valve
    38.00
     Valve
    37.75
    阀
    36.25
     valves
    32.75
    阀门
    31.00
    �
    25.75
    Val
    23.38
    val
    22.88
     VAL
    21.63
    .Val
    21.63
    Activations Density 0.067%

    No Known Activations