© 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. 15446
    Prev
    Next
    INDEX
    Explanations

    say puberty

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

    No Comments

    Negative Logits
    解脱
    -17.63
    擦
    -17.50
    窒息
    -16.13
    谞
    -15.81
    クリ
    -15.75
     ERC
    -15.50
    箓
    -15.19
    ARP
    -15.13
     MCS
    -15.00
    悯
    -15.00
    POSITIVE LOGITS
     puberty
    20.00
    growth
    19.63
     matures
    19.13
    pub
    19.00
    长大了
    18.63
     growth
    18.50
     maturity
    18.38
    Pub
    18.00
     pub
    17.75
     Growth
    17.63
    Activations Density 0.214%

    No Known Activations