© 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
    3. Qwen3-1.7B
    5. 27-LLAMASCOPE-2-LORSA-16K-K64
    7. 15619
    Prev
    Next
    INDEX
    Explanations

    say "criteria"

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

    No Comments

    Negative Logits
    borg
    -18.75
    vault
    -18.00
    Vault
    -17.25
     vagina
    -17.13
    votes
    -17.13
    狱
    -16.25
    outers
    -16.13
     vot
    -16.00
     TOUCH
    -15.94
    vote
    -15.88
    POSITIVE LOGITS
    指令
    16.50
     instruction
    15.25
    /tasks
    14.94
     instructions
    14.38
     Tasks
    14.06
    任务
    13.94
     Instruction
    13.63
     task
    13.63
    LocalizedString
    13.31
    elf
    12.81
    Activations Density 0.025%

    No Known Activations