© 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. 2254
    Prev
    Next
    INDEX
    Explanations

    say crypto

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

    No Comments

    Negative Logits
    [res
    -16.25
    ån
    -16.13
    (sim
    -15.81
    =res
    -15.81
    Ģ
    -15.69
    Sim
    -15.50
     tab
    -15.38
    Tab
    -15.38
     Tab
    -14.94
     mult
    -14.88
    POSITIVE LOGITS
     crypto
    50.50
    Crypto
    47.50
     Crypto
    47.50
    crypto
    44.75
    /crypto
    43.25
    _crypto
    38.75
    .crypto
    37.75
    _CRYPTO
    32.75
    rypto
    31.63
    CRYPT
    28.38
    Activations Density 0.022%

    No Known Activations