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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-1.7B
    5. 27-LLAMASCOPE-2-LORSA-16K-K64
    7. 16028
    Prev
    Next
    INDEX
    Explanations

    say ic

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

    No Comments

    Negative Logits
    itori
    -16.50
    淋
    -16.38
    淹没
    -15.69
    anza
    -15.56
    ajo
    -15.50
    狩
    -15.44
    沐浴
    -15.31
     Shelby
    -15.25
    iffin
    -15.13
    准入
    -15.13
    POSITIVE LOGITS
    ics
    31.50
    ICS
    30.00
    icos
    29.13
    eric
    27.25
     ic
    27.25
    /ic
    26.38
    ERIC
    26.00
    _ic
    25.88
    .ic
    24.63
    icas
    24.50
    Activations Density 0.074%

    No Known Activations