© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-1.7B
    5. 27-LLAMASCOPE-2-LORSA-16K-K64
    7. 15200
    Prev
    Next
    INDEX
    Explanations

    height measurements

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

    No Comments

    Negative Logits
    乔丹
    -19.75
     ########.
    -17.50
    丕
    -17.38
     PCs
    -15.75
    PUT
    -15.25
    歹
    -15.25
    投标人
    -15.19
    不确定性
    -15.19
    巢
    -15.13
    /met
    -15.06
    POSITIVE LOGITS
    _clock
    17.88
    vy
    16.50
    K
    16.50
    linky
    15.44
    小康
    15.31
     K
    15.06
    穰
    15.06
    嗪
    14.81
    科
    14.81
    -k
    14.81
    Activations Density 0.052%

    No Known Activations