© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Qwen3-1.7B
    3. 27-LLAMASCOPE-2-LORSA-16K-K64
    4. 15462
    Prev
    Next
    INDEX
    Explanations

    say "ion"

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

    No Comments

    Negative Logits
    鲁
    -17.13
    笃
    -16.38
    鄙
    -15.75
    aminer
    -15.50
    radi
    -15.44
    rouw
    -15.25
    urm
    -14.88
    .radius
    -14.75
    ppv
    -14.69
    _radi
    -14.56
    POSITIVE LOGITS
    ions
    32.50
    ion
    29.63
    IONS
    28.63
     ion
    28.50
    ION
    28.38
    ionic
    27.88
    iones
    27.75
    ioni
    27.00
    离子
    26.50
    ione
    26.25
    Activations Density 0.039%

    No Known Activations