© 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. 26-LLAMASCOPE-2-LORSA-16K-K64
    7. 1271
    Prev
    Next
    INDEX
    Explanations

    [wood] => [and]

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

    No Comments

    Negative Logits
     wood
    -57.75
    木
    -55.00
     Wood
    -51.75
    Wood
    -50.75
    木材
    -50.50
    wood
    -47.50
    木质
    -45.25
    WOOD
    -41.25
     wooden
    -40.75
     woods
    -39.25
    POSITIVE LOGITS
    贩
    14.81
    eeper
    14.19
    疼痛
    14.13
    艺术家
    14.00
     Israel
    13.69
    reator
    13.63
    渑
    13.56
     CrossRef
    13.44
    Energy
    13.31
    dzi
    13.06
    Activations Density 0.070%

    No Known Activations