© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-1.7B
    5. 27-LLAMASCOPE-2-LORSA-16K-K64
    7. 16251
    Prev
    Next
    INDEX
    Explanations

    精神

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

    No Comments

    Negative Logits
     Hernandez
    -17.50
    Apis
    -15.81
    ernes
    -15.25
     change
    -14.75
    -mini
    -14.63
     Erotic
    -14.50
     integ
    -14.50
     spd
    -14.38
     spur
    -14.31
    borg
    -14.19
    POSITIVE LOGITS
    mat
    17.38
    _countries
    17.13
    (country
    17.13
    country
    17.00
     mat
    16.88
     countries
    16.75
    _MAT
    16.75
    _LAYER
    16.25
    	mat
    16.00
    _COUNTRY
    16.00
    Activations Density 0.051%

    No Known Activations