© 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. 15832
    Prev
    Next
    INDEX
    Explanations

    say horror words

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

    No Comments

    Negative Logits
    -fields
    -17.13
    流动性
    -16.38
    .transaction
    -16.25
    ridge
    -16.00
    bee
    -15.88
     Fields
    -15.81
    分配
    -15.75
    hone
    -15.56
    _NUMERIC
    -15.38
     Fairfield
    -15.31
    POSITIVE LOGITS
    恐怖
    30.25
     horror
    26.88
     terror
    25.25
    恐惧
    24.88
    怖
    23.75
     Horror
    23.63
     spooky
    23.25
    _ghost
    23.13
    terror
    22.38
     eerie
    22.00
    Activations Density 0.225%

    No Known Activations