© 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. 899
    Prev
    Next
    INDEX
    Explanations

    say "places"

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

    No Comments

    Negative Logits
     parachute
    -18.75
    	tree
    -18.00
    -road
    -17.88
    _ped
    -17.63
    土壤
    -17.25
    嫦
    -17.25
    行李
    -17.13
    猿
    -17.13
     Blanch
    -17.13
     ROAD
    -17.13
    POSITIVE LOGITS
    秦皇岛
    19.38
    tor
    17.38
    宝鸡
    16.50
    滨州
    16.38
    辽宁
    15.38
    潍坊
    15.31
    宁县
    15.19
     Norfolk
    14.81
     Virginia
    14.50
    orio
    14.38
    Activations Density 0.211%

    No Known Activations